新增可读文本提取 + 历史记录分页管理

- 新增 text 动作：提取页面可读文本（innerText + 空行/行尾清理，剔除脚本样式标签），agent-browser 与 playwright 双后端支持，自动提取页面标题 - 提取历史持久化(SQLite WAL)：每次捕获自动入库，截图文件存持久化目录 - 新增 API：GET /api/history(分页/类型筛选/搜索)、GET /api/history/<id>(详情)、GET /api/history/<id>/file(截图)、DELETE /api/history/<id> - 前端：新增提取文本选项+干净文本展示；新增提取历史卡片（分页/筛选/搜索/查看弹窗/删除/下载/复制）
恢复端口为16025
2026-08-29 17:37:43 +08:00 · 2026-07-07 13:23:36 +08:00
11 changed files with 863 additions and 56 deletions
@@ -31,6 +31,9 @@ captures/
 *.png
 *.html

+# 运行时数据（历史记录数据库 + 截图文件）
+data/
+
 # 环境变量
 .env
 .env.local
@@ -49,10 +49,10 @@ COPY . .
 # 创建临时目录
 RUN mkdir -p /tmp/web_captures

-EXPOSE 16026
+EXPOSE 16025

 # 健康检查
 HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:16026/health || exit 1
+    CMD curl -f http://localhost:16025/health || exit 1

-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16026", "--timeout", "120", "app:app"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16025", "--timeout", "120", "app:app"]
@@ -6,7 +6,7 @@
 - **当前版本**: v1.0.2
 - **提交历史**:
  - v1.0.0: 初始化项目
-  - v1.0.1: 修改端口为 16026
+  - v1.0.1: 修改端口为 16025
  - v1.0.2: 修复 agent-browser socket 权限问题

 ## 操作步骤
@@ -39,5 +39,5 @@ git push -u origin master --tags

 ## 服务地址

- Web 界面: http://192.168.0.101:16026
- API 接口: http://192.168.0.101:16026/api/capture
+- Web 界面: http://192.168.0.101:16025
+- API 接口: http://192.168.0.101:16025/api/capture
@@ -104,18 +104,18 @@ API 信息接口

 ```bash
 # 基础截图
-curl -X POST http://localhost:16026/api/capture \
+curl -X POST http://localhost:16025/api/capture \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "action": "screenshot"}' \
  --output screenshot.png

 # 提取HTML
-curl -X POST http://localhost:16026/api/capture \
+curl -X POST http://localhost:16025/api/capture \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "action": "html"}'

 # 滚动加载后全页截图
-curl -X POST http://localhost:16026/api/capture \
+curl -X POST http://localhost:16025/api/capture \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://news.ycombinator.com",
@@ -127,7 +127,7 @@ curl -X POST http://localhost:16026/api/capture \
  --output full_page.png

 # 自定义视口
-curl -X POST http://localhost:16026/api/capture \
+curl -X POST http://localhost:16025/api/capture \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
@@ -144,7 +144,7 @@ import requests

 # 截图
 response = requests.post(
-    'http://localhost:16026/api/capture',
+    'http://localhost:16025/api/capture',
    json={
        'url': 'https://example.com',
        'action': 'screenshot'
@@ -155,7 +155,7 @@ with open('screenshot.png', 'wb') as f:

 # 提取HTML
 response = requests.post(
-    'http://localhost:16026/api/capture',
+    'http://localhost:16025/api/capture',
    json={
        'url': 'https://example.com',
        'action': 'html'
@@ -169,7 +169,7 @@ print(html)

 ```javascript
 // 截图
-const response = await fetch('http://localhost:16026/api/capture', {
+const response = await fetch('http://localhost:16025/api/capture', {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
@@ -182,7 +182,7 @@ const response = await fetch('http://localhost:16026/api/capture', {
 const blob = await response.blob();

 // 提取HTML
-const response = await fetch('http://localhost:16026/api/capture', {
+const response = await fetch('http://localhost:16025/api/capture', {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
@@ -199,7 +199,7 @@ console.log(data.html);
 ### 使用 Gunicorn

 ```bash
-gunicorn -w 4 -b 0.0.0.0:16026 app:app
+gunicorn -w 4 -b 0.0.0.0:16025 app:app
 ```

 ### 使用 Systemd 服务
@@ -230,12 +230,12 @@ RUN playwright install chromium --with-deps

 COPY . .
 EXPOSE 5000
-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16026", "app:app"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16025", "app:app"]
 ```

 ```bash
 docker build -t web-capture-api .
-docker run -p 16026:16026 web-capture-api
+docker run -p 16025:16025 web-capture-api
 ```

 ## 性能优化
@@ -5,8 +5,11 @@ Web Capture API - 网页截图与代码提取服务
 """

 import os
+import re
 import json
 import asyncio
+import sqlite3
+import shutil
 import subprocess
 import tempfile
 import uuid
@@ -53,6 +56,80 @@ CORS(app)
 CAPTURE_DIR = Path(tempfile.gettempdir()) / "web_captures"
 CAPTURE_DIR.mkdir(exist_ok=True)

+# 持久化存储（历史记录）
+PROJECT_DIR = Path(__file__).parent
+DATA_DIR = PROJECT_DIR / "data"
+CAPTURE_DATA_DIR = DATA_DIR / "captures"
+HISTORY_DB = DATA_DIR / "history.db"
+DATA_DIR.mkdir(exist_ok=True)
+CAPTURE_DATA_DIR.mkdir(exist_ok=True)
+
+
+def get_db():
+    """获取数据库连接（多进程安全：WAL + busy_timeout）"""
+    conn = sqlite3.connect(HISTORY_DB, timeout=15)
+    conn.row_factory = sqlite3.Row
+    conn.execute("PRAGMA journal_mode=WAL")
+    conn.execute("PRAGMA busy_timeout=15000")
+    return conn
+
+
+def init_db():
+    """初始化历史记录表"""
+    conn = get_db()
+    conn.execute("""
+        CREATE TABLE IF NOT EXISTS captures (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            url TEXT NOT NULL,
+            title TEXT DEFAULT '',
+            action TEXT NOT NULL,
+            backend TEXT DEFAULT '',
+            status TEXT NOT NULL DEFAULT 'success',
+            file_path TEXT DEFAULT '',
+            content TEXT DEFAULT '',
+            error TEXT DEFAULT '',
+            created_at TEXT NOT NULL
+        )
+    """)
+    conn.commit()
+    conn.close()
+
+
+def save_capture(url, title, action, backend, status, file_path='', content='', error=''):
+    """保存一条提取历史记录"""
+    conn = get_db()
+    cur = conn.execute(
+        "INSERT INTO captures (url, title, action, backend, status, file_path, content, error, created_at) "
+        "VALUES (?,?,?,?,?,?,?,?,?)",
+        (url, title, action, backend, status, file_path, content, error,
+         datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+    )
+    conn.commit()
+    rid = cur.lastrowid
+    conn.close()
+    return rid
+
+
+def persist_screenshot(src_path):
+    """把临时截图复制到持久化目录，供历史记录长期访问"""
+    name = f"{datetime.now().strftime('%Y%m%d_%H%M%S')}_{uuid.uuid4().hex[:8]}.png"
+    dest = CAPTURE_DATA_DIR / name
+    shutil.copy2(src_path, dest)
+    return str(dest)
+
+
+def clean_text(raw):
+    """清理可读文本：去掉行尾空格、压缩多余空行、去掉首尾空白"""
+    if not raw:
+        return ""
+    lines = [ln.rstrip() for ln in raw.split("\n")]
+    text = "\n".join(lines)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+init_db()
+
 # agent-browser socket 目录
 os.environ.setdefault("AGENT_BROWSER_SOCKET_DIR", "/tmp/agent-browser-sockets")
 Path(os.environ["AGENT_BROWSER_SOCKET_DIR"]).mkdir(exist_ok=True, parents=True)
@@ -111,6 +188,38 @@ class AgentBrowserSession:
            timeout=10000
        )
        return success, output, error
+
+    @staticmethod
+    def _decode_eval(output):
+        """agent-browser eval 结果按 JSON 编码返回，这里解码回原始字符串"""
+        if output is None:
+            return ""
+        out = output.strip()
+        try:
+            return json.loads(out)
+        except Exception:
+            # 非 JSON（如数字/布尔/纯文本），去掉可能的外层引号
+            return out.strip('\"\'')
+
+    def get_title(self):
+        """获取页面标题"""
+        success, output, error = self.run(
+            ["eval", "document.title"],
+            timeout=10000
+        )
+        if success:
+            return self._decode_eval(output)
+        return ""
+
+    def get_text(self):
+        """提取页面可读文本（干净内容，剔除脚本/样式/标签）"""
+        success, output, error = self.run(
+            ["eval", "document.body.innerText"],
+            timeout=30000
+        )
+        if success:
+            return True, self._decode_eval(output), ""
+        return False, "", error
    
    def scroll_down(self, pixels=800):
        """向下滚动"""
@@ -165,25 +274,35 @@ def capture_with_agent_browser(
                session.scroll_down(800)
                session.wait(scroll_delay)
        
+        # 提取页面标题
+        title = session.get_title()
+
        # 执行操作
        if action == "screenshot":
            temp_file = CAPTURE_DIR / f"{session.session_id}.png"
            success, _, error = session.screenshot(temp_file, full_page=full_page)
            
            if success and temp_file.exists():
-                return {"success": True, "file_path": str(temp_file)}
+                return {"success": True, "title": title, "file_path": str(temp_file)}
            else:
-                return {"success": False, "error": f"Screenshot failed: {error}"}
+                return {"success": False, "title": title, "error": f"Screenshot failed: {error}"}
        
        elif action == "html":
            success, html, error = session.get_html()
            if success:
-                return {"success": True, "html": html}
+                return {"success": True, "title": title, "html": html}
            else:
-                return {"success": False, "error": f"Get HTML failed: {error}"}
+                return {"success": False, "title": title, "error": f"Get HTML failed: {error}"}
+        
+        elif action == "text":
+            success, raw_text, error = session.get_text()
+            if success:
+                return {"success": True, "title": title, "text": clean_text(raw_text)}
+            else:
+                return {"success": False, "title": title, "error": f"Extract text failed: {error}"}
        
        else:
-            return {"success": False, "error": f"Unknown action: {action}"}
+            return {"success": False, "title": title, "error": f"Unknown action: {action}"}
    
    except Exception as e:
        return {"success": False, "error": str(e)}
@@ -343,19 +462,29 @@ async def capture_with_playwright(
                    await page.wait_for_timeout(scroll_delay)
                await page.wait_for_timeout(500)
            
+            # 提取页面标题
+            try:
+                title = await page.title()
+            except:
+                title = ""
+            
            result = {}
            
            if action == "screenshot":
                temp_file = CAPTURE_DIR / f"{session_id}.png"
                await page.screenshot(path=str(temp_file), full_page=full_page)
-                result = {"success": True, "file_path": str(temp_file)}
+                result = {"success": True, "title": title, "file_path": str(temp_file)}
            
            elif action == "html":
                html = await page.content()
-                result = {"success": True, "html": html}
+                result = {"success": True, "title": title, "html": html}
+            
+            elif action == "text":
+                raw_text = await page.evaluate("document.body.innerText")
+                result = {"success": True, "title": title, "text": clean_text(raw_text)}
            
            else:
-                result = {"success": False, "error": f"Unknown action: {action}"}
+                result = {"success": False, "title": title, "error": f"Unknown action: {action}"}
            
            await browser.close()
            return result
@@ -446,9 +575,11 @@ def capture_webpage(
    if backend == "agent-browser":
        if not AGENT_BROWSER_AVAILABLE:
            return {"success": False, "error": "agent-browser not available"}
-        return capture_with_agent_browser(
+        result = capture_with_agent_browser(
            url, action, scroll_times, scroll_delay, full_page, viewport, wait_time
        )
+        result["backend"] = "agent-browser"
+        return result
    
    elif backend == "playwright":
        if not PLAYWRIGHT_AVAILABLE:
@@ -463,6 +594,7 @@ def capture_webpage(
                )
            )
            loop.close()
+            result["backend"] = "playwright"
            return result
        except Exception as e:
            return {"success": False, "error": str(e)}
@@ -482,18 +614,105 @@ def api_info():
    """API信息"""
    return jsonify({
        "service": "Web Capture API",
-        "version": "2.0.0",
+        "version": "2.1.0",
        "backends": {
            "agent-browser": "available" if AGENT_BROWSER_AVAILABLE else "unavailable",
            "playwright": "available" if PLAYWRIGHT_AVAILABLE else "unavailable"
        },
        "endpoints": {
-            "/api/capture": "POST - Capture webpage screenshot or HTML",
+            "/api/capture": "POST - Capture webpage (screenshot/html/text) + 自动入库历史",
+            "/api/history": "GET - 历史记录分页列表 (?page&page_size&action&search)",
+            "/api/history/<id>": "GET - 历史记录详情 / DELETE - 删除记录",
+            "/api/history/<id>/file": "GET - 读取历史截图文件",
            "/health": "GET - Health check"
        }
    })


+@app.route('/api/history', methods=['GET'])
+def history_list():
+    """
+    历史记录分页列表
+    参数: page(默认1), page_size(默认15, 最大100), action(筛选: all/screenshot/html/text), search(按url/title模糊搜索)
+    """
+    page = max(1, int(request.args.get('page', 1)))
+    page_size = min(100, max(1, int(request.args.get('page_size', 15))))
+    action = request.args.get('action', 'all')
+    search = request.args.get('search', '').strip()
+
+    where = []
+    params = []
+    if action and action != 'all':
+        where.append("action = ?")
+        params.append(action)
+    if search:
+        where.append("(url LIKE ? OR title LIKE ?)")
+        params.append(f"%{search}%")
+        params.append(f"%{search}%")
+    where_sql = (" WHERE " + " AND ".join(where)) if where else ""
+
+    conn = get_db()
+    total = conn.execute(f"SELECT COUNT(*) AS c FROM captures{where_sql}", params).fetchone()["c"]
+    rows = conn.execute(
+        f"SELECT id, url, title, action, backend, status, file_path, created_at, "
+        f"LENGTH(content) AS content_size, substr(content, 1, 200) AS content_preview, error "
+        f"FROM captures{where_sql} ORDER BY id DESC LIMIT ? OFFSET ?",
+        params + [page_size, (page - 1) * page_size]
+    ).fetchall()
+    conn.close()
+
+    records = [dict(r) for r in rows]
+    return jsonify({
+        "success": True,
+        "page": page,
+        "page_size": page_size,
+        "total": total,
+        "total_pages": (total + page_size - 1) // page_size if total else 1,
+        "records": records
+    })
+
+
+@app.route('/api/history/<int:rid>', methods=['GET'])
+def history_detail(rid):
+    """历史记录详情（含完整内容）"""
+    conn = get_db()
+    r = conn.execute("SELECT * FROM captures WHERE id=?", (rid,)).fetchone()
+    conn.close()
+    if not r:
+        return jsonify({"success": False, "error": "记录不存在"}), 404
+    return jsonify({"success": True, "record": dict(r)})
+
+
+@app.route('/api/history/<int:rid>/file', methods=['GET'])
+def history_file(rid):
+    """读取历史截图文件"""
+    conn = get_db()
+    r = conn.execute("SELECT file_path FROM captures WHERE id=?", (rid,)).fetchone()
+    conn.close()
+    if not r or not r["file_path"] or not Path(r["file_path"]).exists():
+        return jsonify({"success": False, "error": "文件不存在或已删除"}), 404
+    return send_file(r["file_path"], mimetype='image/png')
+
+
+@app.route('/api/history/<int:rid>', methods=['DELETE'])
+def history_delete(rid):
+    """删除历史记录（连带删除截图文件）"""
+    conn = get_db()
+    r = conn.execute("SELECT file_path FROM captures WHERE id=?", (rid,)).fetchone()
+    if r:
+        conn.execute("DELETE FROM captures WHERE id=?", (rid,))
+        conn.commit()
+    conn.close()
+    if r and r["file_path"]:
+        fp = Path(r["file_path"])
+        if fp.exists() and str(fp).startswith(str(CAPTURE_DATA_DIR)):
+            try:
+                fp.unlink()
+            except Exception:
+                pass
+    return jsonify({"success": True})
+
+
@app.route('/health')
 def health():
    """健康检查"""
@@ -555,19 +774,27 @@ def capture():
        full_page=full_page,
        viewport=viewport,
        wait_time=wait_time,
-        backend=backend,
-        
-        
+        backend=backend
    )
    
+    backend_used = result.get("backend", backend)
+    title = result.get("title", "")
+    
    if not result["success"]:
+        save_capture(url, title, action, backend_used, "failed", error=result.get("error", ""))
        return jsonify(result), 400
    
    if action == "screenshot":
-        file_path = result["file_path"]
-        return send_file(file_path, mimetype='image/png')
+        persisted = persist_screenshot(result["file_path"])
+        save_capture(url, title, action, backend_used, "success", file_path=persisted)
+        return send_file(persisted, mimetype='image/png')
    
    elif action == "html":
+        save_capture(url, title, action, backend_used, "success", content=result["html"])
+        return jsonify(result)
+    
+    elif action == "text":
+        save_capture(url, title, action, backend_used, "success", content=result["text"])
        return jsonify(result)


@@ -583,5 +810,5 @@ if __name__ == '__main__':
        print("   agent-browser: npm install -g agent-browser && agent-browser install")
        print("   playwright: pip install playwright && playwright install chromium")
    
-    print("\n🚀 Server running on http://0.0.0.0:16026")
-    app.run(host='0.0.0.0', port=16026, debug=True)
+    print("\n🚀 Server running on http://0.0.0.0:16025")
+    app.run(host='0.0.0.0', port=16025, debug=True)
@@ -23,4 +23,4 @@ echo "运行方式："
 echo "  开发模式: python3.12 app.py"
 echo "  生产模式: gunicorn -w 4 -b 0.0.0.0:5000 app:app"
 echo ""
-echo "访问地址: http://localhost:16026"
+echo "访问地址: http://localhost:16025"
@@ -6,14 +6,14 @@ services:
    image: web-capture-api:latest
    container_name: web-capture-api
    ports:
-      - "16026:16026"
+      - "16025:16025"
    environment:
      - TZ=Asia/Shanghai
    volumes:
      - ./captures:/tmp/web_captures
    restart: unless-stopped
    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:16026/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:16025/health"]
      interval: 30s
      timeout: 10s
      retries: 3
@@ -110,7 +110,7 @@ echo "   cd $(pwd)"
 echo "   $PYTHON app.py"
 echo ""
 echo "📖 访问地址:"
-echo "   http://localhost:16026"
+echo "   http://localhost:16025"
 echo ""
 echo "📚 API 文档:"
-echo "   http://localhost:16026/api"
+echo "   http://localhost:16025/api"
@@ -3,7 +3,7 @@
 <head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Web Capture - 网页截图与代码提取</title>
+    <title>Web Capture - 网页截图/HTML/文本提取</title>
    <style>
        * {
            margin: 0;
@@ -77,6 +77,7 @@
        .radio-group {
            display: flex;
            gap: 20px;
+            flex-wrap: wrap;
        }
        
        .radio-label {
@@ -201,16 +202,62 @@
            word-wrap: break-word;
        }
        
+        .result-text {
+            background: #f8f9fa;
+            border: 1px solid #e0e0e0;
+            color: #222;
+            padding: 20px;
+            border-radius: 8px;
+            overflow: auto;
+            max-height: 600px;
+            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+            font-size: 14px;
+            line-height: 1.8;
+            white-space: pre-wrap;
+            word-wrap: break-word;
+        }
+        
        .actions {
            margin-top: 20px;
            display: flex;
            gap: 10px;
+            flex-wrap: wrap;
        }
        
        .btn-secondary {
            background: #6c757d;
            padding: 10px 20px;
            font-size: 14px;
+            width: auto;
+            margin-top: 0;
+        }
+        
+        .btn-small {
+            background: #667eea;
+            color: white;
+            border: none;
+            padding: 6px 14px;
+            font-size: 13px;
+            border-radius: 6px;
+            cursor: pointer;
+            transition: background 0.2s;
+        }
+        
+        .btn-small:hover {
+            background: #5568d8;
+        }
+        
+        .btn-small.danger {
+            background: #dc3545;
+        }
+        
+        .btn-small.danger:hover {
+            background: #c82333;
+        }
+        
+        .btn-small:disabled {
+            opacity: 0.5;
+            cursor: not-allowed;
        }
        
        .error {
@@ -227,6 +274,256 @@
            display: block;
        }
        
+        /* ===== 历史记录区域 ===== */
+        .history-header {
+            display: flex;
+            align-items: center;
+            justify-content: space-between;
+            flex-wrap: wrap;
+            gap: 15px;
+            margin-bottom: 20px;
+        }
+        
+        .history-header h3 {
+            font-size: 1.4em;
+            color: #333;
+        }
+        
+        .history-toolbar {
+            display: flex;
+            gap: 10px;
+            flex-wrap: wrap;
+            align-items: center;
+        }
+        
+        .history-toolbar select,
+        .history-toolbar input[type="text"] {
+            width: auto;
+            min-width: 120px;
+            padding: 8px 12px;
+            font-size: 14px;
+        }
+        
+        .history-toolbar .search-input {
+            min-width: 220px;
+        }
+        
+        .history-count {
+            color: #666;
+            font-size: 14px;
+        }
+        
+        .history-table {
+            width: 100%;
+            border-collapse: collapse;
+        }
+        
+        .history-table th,
+        .history-table td {
+            padding: 12px 10px;
+            text-align: left;
+            border-bottom: 1px solid #eee;
+            vertical-align: middle;
+        }
+        
+        .history-table th {
+            font-size: 13px;
+            color: #666;
+            font-weight: 600;
+            white-space: nowrap;
+        }
+        
+        .history-table td {
+            font-size: 14px;
+        }
+        
+        .history-table tr:hover td {
+            background: #f8f9ff;
+        }
+        
+        .badge {
+            display: inline-block;
+            padding: 3px 10px;
+            border-radius: 20px;
+            font-size: 12px;
+            font-weight: 600;
+            white-space: nowrap;
+        }
+        
+        .badge-screenshot {
+            background: #e3f2fd;
+            color: #1565c0;
+        }
+        
+        .badge-html {
+            background: #fff3e0;
+            color: #e65100;
+        }
+        
+        .badge-text {
+            background: #e8f5e9;
+            color: #2e7d32;
+        }
+        
+        .badge-failed {
+            background: #fdecea;
+            color: #c62828;
+        }
+        
+        .history-url {
+            max-width: 280px;
+            overflow: hidden;
+            text-overflow: ellipsis;
+            white-space: nowrap;
+            color: #1565c0;
+            text-decoration: none;
+            display: inline-block;
+            vertical-align: bottom;
+        }
+        
+        .history-title {
+            max-width: 220px;
+            overflow: hidden;
+            text-overflow: ellipsis;
+            white-space: nowrap;
+            color: #333;
+            display: inline-block;
+            vertical-align: bottom;
+        }
+        
+        .history-empty {
+            text-align: center;
+            padding: 40px;
+            color: #999;
+            font-size: 15px;
+        }
+        
+        .pagination {
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            gap: 8px;
+            margin-top: 20px;
+            flex-wrap: wrap;
+        }
+        
+        .page-btn {
+            min-width: 36px;
+            padding: 7px 12px;
+            border: 1px solid #ddd;
+            background: white;
+            border-radius: 6px;
+            cursor: pointer;
+            font-size: 14px;
+            color: #333;
+            transition: all 0.2s;
+        }
+        
+        .page-btn:hover:not(:disabled) {
+            border-color: #667eea;
+            color: #667eea;
+        }
+        
+        .page-btn.active {
+            background: #667eea;
+            color: white;
+            border-color: #667eea;
+        }
+        
+        .page-btn:disabled {
+            opacity: 0.4;
+            cursor: not-allowed;
+        }
+        
+        .page-info {
+            color: #666;
+            font-size: 14px;
+            white-space: nowrap;
+        }
+        
+        /* ===== 查看详情弹窗 ===== */
+        .modal-overlay {
+            display: none;
+            position: fixed;
+            top: 0;
+            left: 0;
+            right: 0;
+            bottom: 0;
+            background: rgba(0, 0, 0, 0.6);
+            z-index: 1000;
+            padding: 30px;
+            overflow-y: auto;
+        }
+        
+        .modal-overlay.active {
+            display: flex;
+        }
+        
+        .modal {
+            background: white;
+            border-radius: 14px;
+            width: 100%;
+            max-width: 900px;
+            margin: auto;
+            box-shadow: 0 20px 60px rgba(0, 0, 0, 0.4);
+            overflow: hidden;
+        }
+        
+        .modal-header {
+            display: flex;
+            align-items: center;
+            justify-content: space-between;
+            padding: 18px 24px;
+            background: #f8f9fa;
+            border-bottom: 1px solid #eee;
+            gap: 15px;
+            flex-wrap: wrap;
+        }
+        
+        .modal-header h3 {
+            font-size: 16px;
+            color: #333;
+            word-break: break-all;
+        }
+        
+        .modal-meta {
+            padding: 10px 24px;
+            background: #f8f9fa;
+            border-bottom: 1px solid #eee;
+            font-size: 13px;
+            color: #666;
+            display: flex;
+            gap: 20px;
+            flex-wrap: wrap;
+        }
+        
+        .modal-body {
+            padding: 20px 24px;
+            max-height: 70vh;
+            overflow: auto;
+        }
+        
+        .modal-body .result-image {
+            width: 100%;
+        }
+        
+        .modal-close {
+            background: #6c757d;
+            color: white;
+            border: none;
+            width: 32px;
+            height: 32px;
+            border-radius: 50%;
+            font-size: 18px;
+            cursor: pointer;
+            line-height: 1;
+            flex-shrink: 0;
+        }
+        
+        .modal-close:hover {
+            background: #545b62;
+        }
+        
        .api-docs {
            margin-top: 30px;
            padding: 20px;
@@ -254,13 +551,22 @@
            overflow-x: auto;
            margin-top: 10px;
        }
+        
+        @media (max-width: 700px) {
+            .history-table th:nth-child(2),
+            .history-table td:nth-child(2),
+            .history-table th:nth-child(3),
+            .history-table td:nth-child(3) {
+                display: none;
+            }
+        }
    </style>
 </head>
 <body>
    <div class="container">
        <div class="header">
            <h1>🌐 Web Capture</h1>
-            <p>网页截图与代码提取服务</p>
+            <p>网页截图 / HTML / 可读文本 提取服务</p>
        </div>
        
        <div class="card">
@@ -281,6 +587,10 @@
                            <input type="radio" name="action" value="html">
                            📄 提取HTML
                        </label>
+                        <label class="radio-label">
+                            <input type="radio" name="action" value="text">
+                            📝 提取文本
+                        </label>
                    </div>
                </div>
                
@@ -350,25 +660,87 @@
            </div>
        </div>
        
+        <div class="card">
+            <div class="history-header">
+                <h3>📜 提取历史</h3>
+                <div class="history-toolbar">
+                    <select id="historyActionFilter" onchange="loadHistory(1)">
+                        <option value="all">全部类型</option>
+                        <option value="screenshot">📸 截图</option>
+                        <option value="html">📄 HTML</option>
+                        <option value="text">📝 文本</option>
+                    </select>
+                    <input type="text" class="search-input" id="historySearch" placeholder="🔍 搜索网址/标题..." onkeydown="if(event.key==='Enter')loadHistory(1)">
+                    <button class="btn-small" onclick="loadHistory(1)">搜索</button>
+                    <button class="btn-small" onclick="refreshHistory()">🔄 刷新</button>
+                </div>
+            </div>
+            
+            <div class="history-count" id="historyCount"></div>
+            
+            <div style="overflow-x: auto; margin-top: 10px;">
+                <table class="history-table">
+                    <thead>
+                        <tr>
+                            <th>时间</th>
+                            <th>类型</th>
+                            <th>网址</th>
+                            <th>标题</th>
+                            <th>状态</th>
+                            <th style="text-align: right;">操作</th>
+                        </tr>
+                    </thead>
+                    <tbody id="historyBody"></tbody>
+                </table>
+            </div>
+            
+            <div class="history-empty" id="historyEmpty" style="display: none;">暂无提取记录，先去上方提取一个网页吧 🚀</div>
+            
+            <div class="pagination" id="pagination"></div>
+        </div>
+        
        <div class="card api-docs">
            <h3>📚 使用说明</h3>
            <p><strong>重要提示：</strong></p>
            <ul style="margin: 10px 0; line-height: 1.8;">
+                <li>📝 <strong>提取文本</strong>：自动剔除脚本/样式/标签，得到干净的前端可读文本，适合直接用于分析/喂给大模型</li>
                <li>⏱️ <strong>页面加载等待</strong>：某些网站需要验证过程（如 Cloudflare），请设置较长时间（10000-30000ms）</li>
                <li>🔄 <strong>滚动次数</strong>：用于加载动态内容（如微博、推特等），建议 3-5 次</li>
                <li>🎯 <strong>全页截图</strong>：滚动加载后建议开启此选项</li>
+                <li>📜 <strong>提取历史</strong>：每次提取自动入库，支持分页浏览、按类型筛选、搜索与删除</li>
            </ul>
            <p style="margin-top: 15px;"><strong>API 调用：</strong></p>
            <pre><code>POST /api/capture
 {
  "url": "https://example.com",
-  "action": "screenshot",  // 或 "html"
-  "wait_time": 15000,     // 重要！验证网站需设置较长等待
-  "scroll_times": 3,      // 可选：加载动态内容
-  "scroll_delay": 1000,  // 可选：滚动间隔
-  "full_page": true,     // 可选：全页截图
-  "backend": "playwright" // 可选：playwright 或 agent-browser
-}</code></pre>
+  "action": "text",           // "screenshot" | "html" | "text"
+  "wait_time": 15000,         // 重要！验证网站需设置较长等待
+  "scroll_times": 3,          // 可选：加载动态内容
+  "scroll_delay": 1000,       // 可选：滚动间隔
+  "full_page": true,          // 可选：全页截图
+  "backend": "playwright"     // 可选：playwright / agent-browser
+}
+
+GET /api/history?page=1&page_size=15&action=all&search=关键词   // 历史分页
+GET /api/history/&lt;id&gt;                                         // 历史详情
+GET /api/history/&lt;id&gt;/file                                     // 历史截图文件
+DELETE /api/history/&lt;id&gt;                                        // 删除历史</code></pre>
+        </div>
+    </div>
+    
+    <!-- 历史详情弹窗 -->
+    <div class="modal-overlay" id="modalOverlay" onclick="if(event.target===this)closeModal()">
+        <div class="modal">
+            <div class="modal-header">
+                <h3 id="modalTitle">记录详情</h3>
+                <button class="modal-close" onclick="closeModal()">✕</button>
+            </div>
+            <div class="modal-meta" id="modalMeta"></div>
+            <div class="modal-body" id="modalBody"></div>
+            <div class="actions" style="padding: 0 24px 20px;">
+                <button class="btn btn-secondary" onclick="downloadHistoryContent()">💾 下载内容</button>
+                <button class="btn btn-secondary" onclick="copyHistoryContent()">📋 复制内容</button>
+            </div>
        </div>
    </div>
    
@@ -380,6 +752,12 @@
        const submitBtn = document.getElementById('submitBtn');
        let currentData = null;
        let currentBlob = null;
+        let currentPage = 1;
+        let currentHistory = { page: 1, total: 0, total_pages: 1 };
+        let modalRecord = null;
+        
+        // 页面加载时读取历史
+        window.addEventListener('load', () => loadHistory(1));
        
        form.addEventListener('submit', async (e) => {
            e.preventDefault();
@@ -429,16 +807,26 @@
                if (action === 'screenshot') {
                    currentBlob = await response.blob();
                    const imageUrl = URL.createObjectURL(currentBlob);
-                    document.getElementById('resultContent').innerHTML = 
+                    document.getElementById('resultContent').innerHTML =
                        `<img src="${imageUrl}" class="result-image" alt="截图结果">`;
                } else {
                    const data = await response.json();
-                    currentBlob = new Blob([data.html], { type: 'text/html' });
-                    document.getElementById('resultContent').innerHTML = 
-                        `<div class="result-code"><pre>${escapeHtml(data.html)}</pre></div>`;
+                    if (action === 'html') {
+                        currentBlob = new Blob([data.html], { type: 'text/html' });
+                        document.getElementById('resultContent').innerHTML =
+                            `<div class="result-code"><pre>${escapeHtml(data.html)}</pre></div>`;
+                    } else {
+                        currentBlob = new Blob([data.text], { type: 'text/plain;charset=utf-8' });
+                        const lines = (data.text || '').split('\n').length;
+                        document.getElementById('resultContent').innerHTML =
+                            `<div style="margin-bottom:10px;color:#666;font-size:13px;">页面标题：${escapeHtml(data.title || '无')} ｜ 共 ${lines} 行，${(data.text || '').length} 字符（已剔除标签与无效字符）</div>` +
+                            `<div class="result-text">${escapeHtml(data.text || '')}</div>`;
+                    }
                }
                
                result.classList.add('active');
+                // 捕获成功后刷新历史（回到第一页看最新）
+                loadHistory(1);
            } catch (err) {
                error.textContent = '❌ ' + err.message;
                error.classList.add('active');
@@ -460,7 +848,9 @@
            const url = URL.createObjectURL(currentBlob);
            const a = document.createElement('a');
            a.href = url;
-            a.download = currentData.action === 'screenshot' ? 'screenshot.png' : 'page.html';
+            const name = currentData.action === 'screenshot' ? 'screenshot.png'
+                       : currentData.action === 'html' ? 'page.html' : 'page.txt';
+            a.download = name;
            a.click();
            URL.revokeObjectURL(url);
        }
@@ -483,6 +873,193 @@
            currentData = null;
            currentBlob = null;
        }
+        
+        /* ===== 历史记录 ===== */
+        async function loadHistory(page) {
+            const action = document.getElementById('historyActionFilter').value;
+            const search = document.getElementById('historySearch').value.trim();
+            const qs = new URLSearchParams({ page: page, page_size: 15, action, search });
+            const res = await fetch('/api/history?' + qs.toString());
+            const data = await res.json();
+            
+            if (!data.success) {
+                document.getElementById('historyEmpty').style.display = 'block';
+                document.getElementById('historyEmpty').textContent = '❌ 加载历史失败：' + (data.error || '未知错误');
+                return;
+            }
+            
+            currentPage = page;
+            currentHistory = data;
+            renderHistory(data);
+        }
+        
+        function refreshHistory() {
+            loadHistory(currentPage);
+        }
+        
+        function renderHistory(data) {
+            const body = document.getElementById('historyBody');
+            const empty = document.getElementById('historyEmpty');
+            const count = document.getElementById('historyCount');
+            
+            count.textContent = `共 ${data.total} 条记录`;
+            
+            if (!data.records.length) {
+                body.innerHTML = '';
+                empty.style.display = 'block';
+                empty.textContent = '暂无提取记录，先去上方提取一个网页吧 🚀';
+                renderPagination(data);
+                return;
+            }
+            empty.style.display = 'none';
+            
+            const badges = {
+                screenshot: '📸 截图',
+                html: '📄 HTML',
+                text: '📝 文本'
+            };
+            
+            body.innerHTML = data.records.map(r => {
+                const badgeClass = r.status === 'failed' ? 'badge-failed' : ('badge-' + r.action);
+                const badgeText = r.status === 'failed' ? '❌ 失败' : (badges[r.action] || r.action);
+                const statusText = r.status === 'failed'
+                    ? `<span style="color:#c62828;" title="${escapeHtml(r.error || '')}">失败</span>`
+                    : '<span style="color:#2e7d32;">成功</span>';
+                return `<tr>
+                    <td style="white-space:nowrap;">${escapeHtml(r.created_at)}</td>
+                    <td><span class="badge ${escapeHtml(badgeClass)}">${badgeText}</span></td>
+                    <td><a class="history-url" href="${escapeHtml(r.url)}" target="_blank" rel="noopener">${escapeHtml(r.url)}</a></td>
+                    <td><span class="history-title" title="${escapeHtml(r.title || '')}">${escapeHtml(r.title || '—')}</span></td>
+                    <td>${statusText}</td>
+                    <td style="text-align:right; white-space:nowrap;">
+                        <button class="btn-small" onclick="viewRecord(${r.id})">👁 查看</button>
+                        <button class="btn-small danger" onclick="deleteRecord(${r.id})">🗑</button>
+                    </td>
+                </tr>`;
+            }).join('');
+            
+            renderPagination(data);
+        }
+        
+        function renderPagination(data) {
+            const el = document.getElementById('pagination');
+            if (!data.records.length) {
+                el.innerHTML = '';
+                return;
+            }
+            
+            let html = '';
+            html += `<button class="page-btn" onclick="loadHistory(${data.page - 1})" ${data.page <= 1 ? 'disabled' : ''}>‹ 上一页</button>`;
+            
+            const total = data.total_pages;
+            const cur = data.page;
+            let start = Math.max(1, cur - 2);
+            let end = Math.min(total, cur + 2);
+            if (end - start < 4) {
+                start = Math.max(1, end - 4);
+                end = Math.min(total, start + 4);
+            }
+            
+            if (start > 1) html += `<button class="page-btn" onclick="loadHistory(1)">1</button>`;
+            if (start > 2) html += `<span style="color:#999;">…</span>`;
+            for (let p = start; p <= end; p++) {
+                html += `<button class="page-btn ${p === cur ? 'active' : ''}" onclick="loadHistory(${p})">${p}</button>`;
+            }
+            if (end < total - 1) html += `<span style="color:#999;">…</span>`;
+            if (end < total) html += `<button class="page-btn" onclick="loadHistory(${total})">${total}</button>`;
+            
+            html += `<button class="page-btn" onclick="loadHistory(${data.page + 1})" ${data.page >= total ? 'disabled' : ''}>下一页 ›</button>`;
+            html += `<span class="page-info">第 ${data.page} / ${total} 页</span>`;
+            
+            el.innerHTML = html;
+        }
+        
+        async function viewRecord(id) {
+            const res = await fetch('/api/history/' + id);
+            const data = await res.json();
+            if (!data.success) {
+                alert('加载失败：' + (data.error || '未知错误'));
+                return;
+            }
+            modalRecord = data.record;
+            const r = modalRecord;
+            
+            document.getElementById('modalTitle').textContent = (r.title || r.url || '记录详情');
+            const badgeClass = r.status === 'failed' ? 'badge-failed' : ('badge-' + r.action);
+            const badgeText = r.status === 'failed' ? '❌ 失败' : ({screenshot: '📸 截图', html: '📄 HTML', text: '📝 文本'}[r.action] || r.action);
+            document.getElementById('modalMeta').innerHTML =
+                `<span>类型：<span class="badge ${badgeClass}">${badgeText}</span></span>` +
+                `<span>时间：${escapeHtml(r.created_at)}</span>` +
+                `<span>后端：${escapeHtml(r.backend || '—')}</span>` +
+                `<span>状态：${r.status === 'failed' ? '<span style="color:#c62828;">失败</span>' : '<span style="color:#2e7d32;">成功</span>'}</span>`;
+            
+            const body = document.getElementById('modalBody');
+            if (r.status === 'failed') {
+                body.innerHTML = `<div class="result-text" style="color:#c62828;">❌ 提取失败：${escapeHtml(r.error || '')}</div>`;
+            } else if (r.action === 'screenshot') {
+                body.innerHTML = `<img src="/api/history/${r.id}/file" class="result-image" alt="历史截图" onerror="this.parentElement.innerHTML='&lt;p style=&quot;color:#c62828;&quot;&gt;截图文件不存在或已删除&lt;/p&gt;'">`;
+            } else if (r.action === 'html') {
+                body.innerHTML = `<div class="result-code"><pre>${escapeHtml(r.content || '')}</pre></div>`;
+            } else {
+                body.innerHTML = `<div class="result-text">${escapeHtml(r.content || '')}</div>`;
+            }
+            
+            document.getElementById('modalOverlay').classList.add('active');
+        }
+        
+        function closeModal() {
+            document.getElementById('modalOverlay').classList.remove('active');
+            modalRecord = null;
+        }
+        
+        async function deleteRecord(id) {
+            if (!confirm('确定删除这条记录吗？截图文件将一并删除。')) return;
+            const res = await fetch('/api/history/' + id, { method: 'DELETE' });
+            const data = await res.json();
+            if (data.success) {
+                // 若当前页删空了则回退一页
+                if (currentHistory.records.length === 1 && currentPage > 1) {
+                    loadHistory(currentPage - 1);
+                } else {
+                    loadHistory(currentPage);
+                }
+            } else {
+                alert('删除失败：' + (data.error || '未知错误'));
+            }
+        }
+        
+        function currentModalBlob() {
+            if (!modalRecord) return null;
+            if (modalRecord.action === 'screenshot') return null; // 图片用链接下载
+            const type = modalRecord.action === 'html' ? 'text/html' : 'text/plain;charset=utf-8';
+            return new Blob([modalRecord.content || ''], { type });
+        }
+        
+        function downloadHistoryContent() {
+            if (!modalRecord) return;
+            if (modalRecord.action === 'screenshot') {
+                const a = document.createElement('a');
+                a.href = `/api/history/${modalRecord.id}/file`;
+                a.download = `capture_${modalRecord.id}.png`;
+                a.click();
+                return;
+            }
+            const blob = currentModalBlob();
+            if (!blob) return;
+            const url = URL.createObjectURL(blob);
+            const a = document.createElement('a');
+            a.href = url;
+            a.download = modalRecord.action === 'html' ? `page_${modalRecord.id}.html` : `page_${modalRecord.id}.txt`;
+            a.click();
+            URL.revokeObjectURL(url);
+        }
+        
+        function copyHistoryContent() {
+            if (!modalRecord || !modalRecord.content) return;
+            navigator.clipboard.writeText(modalRecord.content).then(() => {
+                alert('已复制到剪贴板');
+            });
+        }
    </script>
 </body>
 </html>
@@ -7,7 +7,7 @@ import requests
 import json
 import sys

-API_URL = "http://localhost:16026"
+API_URL = "http://localhost:16025"


 def test_health():
@@ -6,7 +6,7 @@ After=network.target
 Type=simple
 User=openclaw
 WorkingDirectory=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api
-ExecStart=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api/venv/bin/gunicorn -w 4 -b 0.0.0.0:16026 app:app
+ExecStart=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api/venv/bin/gunicorn -w 4 -b 0.0.0.0:16025 app:app
 Restart=always
 RestartSec=10