数据处理功能更新

.gitignore

@@ -19,3 +19,10 @@ test_*.py
 mirror/
 *_mirror/
 test_mirror_*/
+
+#混淆脚本
+obfuscate_pages.py
+obfuscate_config.json
+
+#示例文件
+examples/

README.md

@@ -44,6 +44,12 @@ print(response.cf_colo)  # 可能显示 NRT, SIN, LAX 等不同节点
 - [点击观看 B 站视频教程](https://b23.tv/1uzOf7M)
 - [点击观看 YouTube 视频教程](https://youtu.be/oPeXiIFJ9TA?si=ukXsX8iP86ZTB4LP)
 
+**代码演示视频 - 快速上手**
+
+观看完整的爬虫示例演示，了解如何使用 CFspider 进行数据提取和批量处理：
+
+- [点击观看代码演示视频](examples/scraper_demo.mp4) - 8 行代码完成爬虫示例
+
 > ⚠️ **重要声明**：本项目仅供学习研究、网络安全测试、合规数据采集等**合法用途**。使用者须遵守所在地法律法规及 Cloudflare 服务条款。**任何非法使用（包括但不限于网络攻击、侵犯隐私、规避版权保护等）均与本项目开发者无关，使用者自行承担全部法律责任。**
 
 ## 代理方案对比

test.py

@@ -1,43 +1,9 @@
+import CodeVideoRenderer
+
+CodeVideoRenderer.CameraFollowCursorCV(code_string="""
 import cfspider
 
-# ========== 方案一：使用有效的 Workers 地址 ==========
-# 请将下面的地址替换为你的实际 Workers 地址
-# Workers 地址格式：https://your-worker-name.your-subdomain.workers.dev
-WORKERS_URL = "https://proxy.kami666.xyz/"  # 替换为你的 Workers 地址
-TOKEN = "HAIfuge27"  # 替换为你在 Workers 中配置的 token
+response = cfspider.get("https://www.cfspider.com",impersonate="chrome131")
 
-try:
-    # 使用 Token 鉴权的请求
-    res = cfspider.get(
-        "https://httpbin.org/ip",
-        cf_proxies=WORKERS_URL,
-        token=TOKEN 
-    )
-    
-    print("✅ 请求成功！")
-    print(f"响应内容: {res.text}")
-    print(f"节点代码: {res.cf_colo}")
-    print(f"Ray ID: {res.cf_ray}")
-    print(f"状态码: {res.status_code}")
-    
-except Exception as e:
-    print(f"❌ 请求失败: {e}")
-    print("\n可能的原因：")
-    print("1. Workers 地址不正确或域名无法解析")
-    print("2. Token 配置错误")
-    print("3. 网络连接问题")
-    print("\n解决方案：")
-    print("1. 检查 Workers 地址是否正确")
-    print("2. 确认 Workers 已部署并运行")
-    print("3. 检查 Token 是否在 Workers 环境变量中配置")
-    print("4. 尝试不使用代理测试（见下方方案二）")
-
-# ========== 方案二：不使用代理测试（用于验证库是否正常）==========
-print("\n" + "="*50)
-print("测试：不使用代理直接请求")
-try:
-    res = cfspider.get("https://httpbin.org/ip")
-    print("✅ 直接请求成功！")
-    print(f"响应内容: {res.text}")
-except Exception as e:
-    print(f"❌ 直接请求也失败: {e}")
+print(response.text)
+""")

workers.js

@@ -1,8 +1,8 @@
-// CFspider - Cloudflare Workers 代理 IP 池 v1.7.3
+// CFspider - Cloudflare Workers 代理 IP 池 v1.8.0
 // 支持：同步/异步请求、TLS指纹模拟、浏览器自动化
 
 let 反代IP = '';
-const VERSION = '1.7.3';
+const VERSION = '1.8.0';
 const START_TIME = Date.now();
 
 export default {
@@ -31,8 +31,12 @@ export default {
             return new Response(null, { headers: corsHeaders });
         }
         
-        // Token 验证（除了首页和 debug 页面）
-        if (path !== '' && path !== '/' && path !== 'debug') {
+        // Token 验证（除了首页、debug 页面和从首页发起的 API 请求）
+        const referer = request.headers.get('Referer') || '';
+        const isFromHomePage = referer && (referer.endsWith('/') || referer.endsWith(url.hostname + '/') || referer.includes(url.hostname + '/?'));
+        const isPublicApi = (path === 'api/pool' || path === 'api/proxyip') && isFromHomePage;
+        
+        if (path !== '' && path !== '/' && path !== 'debug' && !isPublicApi) {
             const tokenValidation = validateToken(request, env);
             if (!tokenValidation.valid) {
                 return new Response(JSON.stringify({
@@ -1247,7 +1251,7 @@ function generateCyberpunkPage(request, url, visitorIP) {
         </div>
         
         <div class="code-section">
-            <pre><span class="code-comment"># pip install cfspider</span>
+            <pre><span class="code-comment"># pip install cfspider[extract]</span>
 <span class="code-keyword">import</span> cfspider
 
 cf_proxies = <span class="code-string">"https://your-workers.dev"</span>
@@ -1259,12 +1263,24 @@ response = cfspider.<span class="code-function">get</span>(
 )
 <span class="code-function">print</span>(response.cf_colo)  <span class="code-comment"># Cloudflare node code</span>
 
-<span class="code-comment"># TLS fingerprint impersonate (curl_cffi)</span>
+<span class="code-comment"># TLS fingerprint + stealth mode</span>
 response = cfspider.<span class="code-function">get</span>(
     <span class="code-string">"https://example.com"</span>,
-    impersonate=<span class="code-string">"chrome131"</span>
+    impersonate=<span class="code-string">"chrome131"</span>,
+    stealth=<span class="code-keyword">True</span>
 )
 
+<span class="code-comment"># Data extraction (CSS/XPath/JSONPath)</span>
+title = response.<span class="code-function">find</span>(<span class="code-string">"h1"</span>)
+links = response.<span class="code-function">find_all</span>(<span class="code-string">"a"</span>, attr=<span class="code-string">"href"</span>)
+data = response.<span class="code-function">pick</span>(title=<span class="code-string">"h1"</span>, links=(<span class="code-string">"a"</span>, <span class="code-string">"href"</span>))
+data.<span class="code-function">save</span>(<span class="code-string">"output.csv"</span>)
+
+<span class="code-comment"># Batch requests with progress</span>
+urls = [<span class="code-string">"https://example.com/1"</span>, <span class="code-string">"https://example.com/2"</span>]
+results = cfspider.<span class="code-function">batch</span>(urls, concurrency=<span class="code-number">10</span>)
+results.<span class="code-function">save</span>(<span class="code-string">"results.json"</span>)
+
 <span class="code-comment"># Async request (httpx)</span>
 response = <span class="code-keyword">await</span> cfspider.<span class="code-function">aget</span>(
     <span class="code-string">"https://httpbin.org/ip"</span>,
@@ -1293,7 +1309,11 @@ browser.<span class="code-function">close</span>()</pre>
         
         async function loadPool() {
             try {
-                const resp = await fetch('/api/pool');
+                // 从 URL 参数获取 token
+                const urlParams = new URLSearchParams(window.location.search);
+                const token = urlParams.get('token');
+                const apiUrl = token ? \`/api/pool?token=\${token}\` : '/api/pool';
+                const resp = await fetch(apiUrl);
                 const data = await resp.json();
                 const tbody = document.getElementById('poolBody');