feat: 新增电能e招采平台爬虫

- 新增 EspicCrawler 爬虫类，支持电能e招采平台招标信息抓取 - 目标平台：https://ebid.espic.com.cn，专注于电力行业电子招投标 - 智能 URL 生成：使用 getUrl() 方法动态生成带时间戳的分页链接 - 增强反 WAF 功能：等待人机识别检测通过，避免被防火墙拦截 - 多重选择器策略：使用多种选择器组合查找下一页按钮，提高翻页成功率 - 使用正则表达式提取招标信息，支持标题、URL和发布日期解析 - 添加完整的人类行为模拟功能（鼠标移动、滚动）降低检测风险 - 支持分页抓取，最多抓取5页数据 - 添加完整的单元测试文件，确保爬虫功能正常 - 统一的错误处理机制，单个爬虫失败不影响整体任务执行
2026-01-12 00:01:38 +08:00
parent bf17587bd3
commit 3454d9d07f
2 changed files with 298 additions and 0 deletions
--- a/src/crawler/services/espic_target.spec.ts
+++ b/src/crawler/services/espic_target.spec.ts
@@ -0,0 +1,51 @@
+import { EspicCrawler } from './espic_target';
+import * as puppeteer from 'puppeteer';
+
+// Increase timeout to 60 seconds for network operations
+jest.setTimeout(60000*5);
+
+describe('EspicCrawler Real Site Test', () => {
+  let browser: puppeteer.Browser;
+
+  beforeAll(async () => {
+    browser = await puppeteer.launch({
+      headless: false, // Change to false to see browser UI
+      args: ['--no-sandbox', '--disable-setuid-sandbox'],
+    });
+  });
+
+  afterAll(async () => {
+    if (browser) {
+      await browser.close();
+    }
+  });
+
+  it('should visit website and list all found bid information', async () => {
+    console.log(`\nStarting crawl for: ${EspicCrawler.name}`);
+    console.log(`Target URL: ${EspicCrawler.getUrl()}`);
+    
+    const results = await EspicCrawler.crawl(browser);
+    
+    console.log(`\nSuccessfully found ${results.length} items:\n`);
+    console.log('----------------------------------------');
+    results.forEach((item, index) => {
+      console.log(`${index + 1}. [${item.publishDate.toLocaleDateString()}] ${item.title}`);
+      console.log(`   Link: ${item.url}`);
+      console.log('----------------------------------------');
+    });
+
+    // Basic assertions to ensure crawler is working
+    expect(results).toBeDefined();
+    expect(Array.isArray(results)).toBeTruthy();
+    // Warn but don't fail if site returns 0 items (could be empty or changed structure)
+    if (results.length === 0) {
+      console.warn('Warning: No items found. Check if website structure has changed or if list is currently empty.');
+    } else {
+       // Check data integrity of first item
+       const firstItem = results[0];
+       expect(firstItem.title).toBeTruthy();
+       expect(firstItem.url).toMatch(/^https?:\/\//);
+       expect(firstItem.publishDate).toBeInstanceOf(Date);
+    }
+  });
+});
--- a/src/crawler/services/espic_target.ts
+++ b/src/crawler/services/espic_target.ts
@@ -0,0 +1,247 @@
+import * as puppeteer from 'puppeteer';
+import { Logger } from '@nestjs/common';
+
+// 模拟人类鼠标移动
+async function simulateHumanMouseMovement(page: puppeteer.Page) {
+  const viewport = page.viewport();
+  if (!viewport) return;
+
+  const movements = 5 + Math.floor(Math.random() * 5); // 5-10次随机移动
+
+  for (let i = 0; i < movements; i++) {
+    const x = Math.floor(Math.random() * viewport.width);
+    const y = Math.floor(Math.random() * viewport.height);
+    
+    await page.mouse.move(x, y, {
+      steps: 10 + Math.floor(Math.random() * 20) // 10-30步，使移动更平滑
+    });
+    
+    // 随机停顿 100-500ms
+    await new Promise(r => setTimeout(r, 100 + Math.random() * 400));
+  }
+}
+
+// 模拟人类滚动
+async function simulateHumanScrolling(page: puppeteer.Page) {
+  const scrollCount = 3 + Math.floor(Math.random() * 5); // 3-7次滚动
+
+  for (let i = 0; i < scrollCount; i++) {
+    const scrollDistance = 100 + Math.floor(Math.random() * 400); // 100-500px
+    
+    await page.evaluate((distance) => {
+      window.scrollBy({
+        top: distance,
+        behavior: 'smooth'
+      });
+    }, scrollDistance);
+
+    // 随机停顿 500-1500ms
+    await new Promise(r => setTimeout(r, 500 + Math.random() * 1000));
+  }
+
+  // 滚动回顶部
+  await page.evaluate(() => {
+    window.scrollTo({ top: 0, behavior: 'smooth' });
+  });
+  await new Promise(r => setTimeout(r, 1000));
+}
+
+export interface EspicResult {
+  title: string;
+  publishDate: Date;
+  url: string;
+}
+
+export const EspicCrawler = {
+  name: '电能e招采平台',
+  baseUrl: 'https://ebid.espic.com.cn',
+
+  // 生成动态 URL，使用当前日期
+  getUrl(page: number = 1): string {
+    const now = new Date();
+    const year = now.getFullYear();
+    const month = now.getMonth() + 1; // 月份从0开始
+    const day = now.getDate();
+    const timeStr = `${year}-${month}-${day}`;
+    return `https://ebid.espic.com.cn/newgdtcms//category/iframe.html?dates=300&categoryId=2&tenderMethod=01&tabName=&page=${page}&time=${timeStr}`;
+  },
+
+  async crawl(browser: puppeteer.Browser): Promise<EspicResult[]> {
+    const logger = new Logger('EspicCrawler');
+    const page = await browser.newPage();
+
+    const username = process.env.PROXY_USERNAME;
+    const password = process.env.PROXY_PASSWORD;
+    if (username && password) {
+      await page.authenticate({ username, password });
+    }
+
+    await page.evaluateOnNewDocument(() => {
+      Object.defineProperty(navigator, 'webdriver', { get: () => false });
+      Object.defineProperty(navigator, 'language', {	get: () => "zh-CN"});
+      Object.defineProperty(navigator, 'plugins', {	get: () => [1,2,3,4,5]});
+    });
+
+    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36');
+    await page.setViewport({ width: 1920, height: 1080 });
+
+    const allResults: EspicResult[] = [];
+    let currentPage = 1;
+    const maxPages = 5;
+
+    try {
+      const url = this.getUrl(currentPage);
+      logger.log(`Navigating to ${url}...`);
+      await page.goto(url, { waitUntil: 'networkidle2', timeout: 60000 });
+
+      // 等待 WAF 验证通过
+      logger.log('Waiting for WAF verification...');
+      await page.waitForFunction(
+        () => {
+          // 检查是否已经通过验证（页面不再是 WAF 页面）
+          const bodyText = document.body?.textContent || '';
+          return !bodyText.includes('人机识别检测') && !bodyText.includes('WEB 应用防火墙');
+        },
+        { timeout: 30000 }
+      );
+
+      // 模拟人类行为
+      logger.log('Simulating human mouse movements...');
+      await simulateHumanMouseMovement(page);
+      
+      logger.log('Simulating human scrolling...');
+      await simulateHumanScrolling(page);
+
+      while (currentPage <= maxPages) {
+        logger.log(`Processing page ${currentPage}...`);
+
+        const content = await page.content();
+        const pageResults = this.extract(content);
+
+        if (pageResults.length === 0) {
+          logger.warn(`No results found on page ${currentPage}, stopping.`);
+          break;
+        }
+
+        allResults.push(...pageResults);
+        logger.log(`Extracted ${pageResults.length} items from page ${currentPage}`);
+
+        // 模拟人类行为 - 翻页前
+        logger.log('Simulating human mouse movements before pagination...');
+        await simulateHumanMouseMovement(page);
+        
+        logger.log('Simulating human scrolling before pagination...');
+        await simulateHumanScrolling(page);
+
+        // 查找下一页按钮 - 根据网站实际结构调整选择器
+        // 实际结构: <a href="javascript:void(0);" onclick="turnPage(2);">下一页</a>
+        const nextButtonSelectors = [
+          'a[onclick*="turnPage"]',
+          'a:contains("下一页")',
+          'a[aria-label="Next"]',
+          'a.next',
+          'li.next a',
+          'a.layui-laypage-next:not(.layui-disabled)'
+        ];
+
+        let nextButton: puppeteer.ElementHandle<Element> | null = null;
+        for (const selector of nextButtonSelectors) {
+          try {
+            nextButton = await page.$(selector);
+            if (nextButton) break;
+          } catch (e) {
+            // 继续尝试下一个选择器
+          }
+        }
+
+        if (!nextButton) {
+          logger.log('Next page button not found. Reached end of list.');
+          break;
+        }
+
+        logger.log(`Navigating to page ${currentPage + 1}...`);
+
+        try {
+          // 点击下一页按钮
+          await nextButton.click();
+          await new Promise(r => setTimeout(r, 3000)); // 等待页面加载
+        } catch (navError) {
+          logger.error(`Navigation to page ${currentPage + 1} failed: ${navError.message}`);
+          break;
+        }
+
+        currentPage++;
+
+        // 模拟人类行为 - 翻页后
+        logger.log('Simulating human mouse movements after pagination...');
+        await simulateHumanMouseMovement(page);
+        
+        logger.log('Simulating human scrolling after pagination...');
+        await simulateHumanScrolling(page);
+
+        // Random delay between pages
+        const delay = Math.floor(Math.random() * (3000 - 1000 + 1)) + 1000;
+        await new Promise(resolve => setTimeout(resolve, delay));
+      }
+
+      return allResults;
+
+    } catch (error) {
+      logger.error(`Failed to crawl ${this.name}: ${error.message}`);
+      return allResults;
+    } finally {
+      await page.close();
+    }
+  },
+
+  extract(html: string): EspicResult[] {
+    const results: EspicResult[] = [];
+    /**
+     * Regex groups for ebid.espic.com.cn:
+     * 1: URL (href属性)
+     * 2: Title (title属性，完整的招标工程名称)
+     * 3: Date (发布时间，格式：2026-01-11)
+     *
+     * HTML结构示例:
+     * <li>
+     *   <a href="https://ebid.espic.com.cn/sdny_bulletin/2026-01-11/977309.html"
+     *      title="GJDTHN2025225-国家电投集团河南公司平顶山发电2026年-2028年（两年期）旺河灰场运维项目招标公告"
+     *      class="clearfix" target="_blank">
+     *     <div class="row">
+     *       <div class="col-10 ">
+     *         <h5>GJDTHN2025225-国家电投集团河南公司平顶山发电2026年-2028年（两年期）旺...</h5>
+     *         <dl class="newsinfo row">
+     *           <dd class="col">招标编号：<span>DNYZC-2026-01-11-001</span></dd>
+     *           <dd class="col">招标方式：<span>公开招标</span></dd>
+     *           <dd class="col">报名截止时间：<span>2026-01-19</span></dd>
+     *         </dl>
+     *       </div>
+     *       <div class="col-2 ">
+     *         <div class="newsDate">
+     *           <div>2026-01-11</div>
+     *         </div>
+     *       </div>
+     *     </div>
+     *   </a>
+     * </li>
+     */
+    const regex = /<li>[\s\S]*?<a[^>]*href="([^"]*)"[^>]*title="([^"]*)"[^>]*>[\s\S]*?<div class="newsDate">[\s\S]*?<div>\s*(\d{4}-\d{2}-\d{2})\s*<\/div>[\s\S]*?<\/div>[\s\S]*?<\/a>[\s\S]*?<\/li>/gs;
+
+    let match;
+    while ((match = regex.exec(html)) !== null) {
+      const url = match[1]?.trim();
+      const title = match[2]?.trim();
+      const dateStr = match[3]?.trim();
+
+      if (title && url) {
+        results.push({
+          title,
+          publishDate: dateStr ? new Date(dateStr) : new Date(),
+          url: url.startsWith('http') ? url : this.baseUrl + url
+        });
+      }
+    }
+
+    return results;
+  }
+};