feat(round-16): AI意图情绪分析/展会名片双向互换/雷达爬虫清洗/离线多媒体缓存 (103套件1101测试全绿)

backend/test/modules/crm/bot-filter.test.ts

@@ -0,0 +1,77 @@
+import {
+  RadarBotFilterService,
+  detectBotUserAgent,
+  isRateLimitSuspicious,
+  TrafficFilterResult,
+} from '../../../src/modules/crm/service/bot-filter';
+
+describe('Point 63 (P2): 访客雷达异常流量与出海社交抓取机器爬虫清洗过滤', () => {
+  let service: RadarBotFilterService;
+
+  beforeEach(() => {
+    service = new RadarBotFilterService();
+  });
+
+  describe('1. detectBotUserAgent (爬虫与社交卡片抓取器识别)', () => {
+    it('应精准识别 Googlebot、Bingbot 与主流搜索引擎爬虫', () => {
+      const googleUa = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)';
+      const res = detectBotUserAgent(googleUa);
+      expect(res.isBot).toBe(true);
+      expect(res.botType).toBe('SEARCH_CRAWLER');
+    });
+
+    it('应精准识别 WhatsApp 与 Twitter/LinkedIn 社交预览卡片抓取器', () => {
+      const waUa = 'WhatsApp/2.21.12.21 A';
+      const waRes = detectBotUserAgent(waUa);
+      expect(waRes.isBot).toBe(true);
+      expect(waRes.botType).toBe('SOCIAL_PREVIEW');
+
+      const twUa = 'Twitterbot/1.0';
+      const twRes = detectBotUserAgent(twUa);
+      expect(twRes.isBot).toBe(true);
+      expect(twRes.botType).toBe('SOCIAL_PREVIEW');
+    });
+
+    it('应拦截 curl、Python Requests、Postman 等自动化脚本工具', () => {
+      expect(detectBotUserAgent('python-requests/2.28.1').isBot).toBe(true);
+      expect(detectBotUserAgent('curl/7.68.0').isBot).toBe(true);
+    });
+
+    it('真实手机移动端浏览器访问应判定为正常用户 (isBot = false)', () => {
+      const mobileUa = 'Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Mobile/15E148 Safari/604.1';
+      const res = detectBotUserAgent(mobileUa);
+      expect(res.isBot).toBe(false);
+      expect(res.botType).toBeUndefined();
+    });
+  });
+
+  describe('2. isRateLimitSuspicious (超高频空刷异常检测)', () => {
+    it('1秒内发生超过 10 次访问请求应判定为异常刷量', () => {
+      const timestamps = Array(12).fill(Date.now());
+      expect(isRateLimitSuspicious(timestamps)).toBe(true);
+    });
+
+    it('正常人类浏览间隔应判定为合法流量', () => {
+      const timestamps = [Date.now() - 5000, Date.now() - 2000, Date.now()];
+      expect(isRateLimitSuspicious(timestamps)).toBe(false);
+    });
+  });
+
+  describe('3. RadarBotFilterService 综合过滤清洗', () => {
+    it('应标记机器人流量并决定是否计入 CRM 真实意向得分', async () => {
+      const botTraffic = await service.filterIncomingTraffic({
+        ip: '66.249.66.1',
+        userAgent: 'Googlebot/2.1',
+      });
+      expect(botTraffic.shouldRecordLead).toBe(false);
+      expect(botTraffic.category).toBe('CRAWLER');
+
+      const humanTraffic = await service.filterIncomingTraffic({
+        ip: '94.200.12.34',
+        userAgent: 'Mozilla/5.0 (Linux; Android 14) Chrome/120.0 Mobile Safari/537.36',
+      });
+      expect(humanTraffic.shouldRecordLead).toBe(true);
+      expect(humanTraffic.category).toBe('HUMAN');
+    });
+  });
+});