🚀 Auto-deploy: 27b0c30bc71c932c4699cdd45f05255ae06d4b3e

server.ts

@@ -38,10 +38,10 @@ app.get('/health', (req, res) => {
 // 2. 执行爬取任务接口
 app.post('/crawl', async (req, res) => {
   try {
-    const { paltform, urls, preset = 'stable' } = req.body;
+    const { platform, urls, preset = 'stable' } = req.body;
 
     // 参数验证
-    if (!paltform || typeof paltform !== 'string') {
+    if (!platform || typeof platform !== 'string') {
       return res.status(400).json({ 
         success: false, 
         error: '请提供有效的 platform 参数 (例如: "Otto")' 
@@ -56,22 +56,22 @@ app.post('/crawl', async (req, res) => {
     }
 
     // 检查是否支持该源
-    if (!(paltform in crawlerMap)) {
+    if (!(platform in crawlerMap)) {
       return res.status(400).json({ 
         success: false, 
-        error: `不支持的爬虫源: ${paltform}。支持的源: ${Object.keys(crawlerMap).join(', ')}` 
+        error: `不支持的爬虫源: ${platform}。支持的源: ${Object.keys(crawlerMap).join(', ')}` 
       });
     }
 
-    log.info(`[API] 收到爬取请求: paltform=${paltform}, ${urls.length} 个 URL, preset=${preset}`);
+    log.info(`[API] 收到爬取请求: platform=${platform}, ${urls.length} 个 URL, preset=${preset}`);
 
-    // 根据 paltform 选择对应的爬虫执行
-    const crawler = crawlerMap[paltform as CrawlerPlatform];
+    // 根据 platform 选择对应的爬虫执行
+    const crawler = crawlerMap[platform as CrawlerPlatform];
     const results: ProductData[] = await crawler(urls, { preset });
 
     res.json({
       success: true,
-      paltform: paltform,
+      platform: platform,
       count: results.length,
       data: results
     });

src/config.ts

@@ -14,11 +14,11 @@ export interface CrawlerConfig {
     args?: string[];
   };
   selectors: {
+    brand: string[];
     price: string[];
+    originalPrice: string[];
     rating: string[];
     reviews: string[];
-    title?: string[];
-    imageUrl?: string[];
   };
 }
 
@@ -107,35 +107,20 @@ const PRESETS: Record<string, Partial<CrawlerConfig>> = {
 
 export const DEFAULT_SELECTORS = {
   // 标题选择器 - 用于智能等待判断页面是否加载完成
-  title: [
-    'h1.pdp-product-title',
-    'h1[data-test="product-title"]',
-    '.product-title h1',
-    'div.pdp_short-info__main-name'
+  brand: [
+    '.js_pdp_short-info__brand-link'
   ],
   price: [
-    'span[data-test="price-current"]',
-    'span.js_pdp_price__current-price',
-    '.price--current',
-    '[data-test="product-price"]',
     'span.js_pdp_price__retail-price__value_original'
   ],
+  originalPrice: [
+    'span.pdp_price__strike-through-price'
+  ],
   rating: [
-    'div[data-test="rating-score"]',
-    'div.pdp_cr-rating-score span',
-    '.rating-stars',
-    '[data-test="average-rating"]'
+    'div.pdp_cr-rating-score span'
   ],
   reviews: [
-    'span[data-test="review-count"]',
-    'span.js_pdp_cr-rating--review-count',
-    '.review-count-text',
-    '[data-test="total-reviews"]'
-  ],
-  imageUrl: [
-    'img[data-test="product-image"]',
-    '.pdp-gallery__active img',
-    'meta[property="og:image"]'
+    'span.js_pdp_cr-rating--review-count'
   ]
 };
 

src/otto-crawler.ts

@@ -8,6 +8,7 @@ let currentConfig: CrawlerConfig = getCrawlerConfig();
 export interface ProductData {
   url: string;
   crawledAt: string;
+  brand?: string | null;
   price?: string | null;
   rating?: string | null;
   reviews?: string | null;
@@ -44,10 +45,17 @@ async function extractText(page: Page, ...selectors: string[]): Promise<string |
 async function extractOttoData(page: Page, product: ProductData = {} as ProductData): Promise<ProductData> {
   try {
     const selectors = currentConfig.selectors;
+
+    // 提取品牌
+    const brand = await extractText(page, ...selectors.brand);
+    if (brand) product.brand = brand;
     
     // 提取价格
     const price = await extractText(page, ...selectors.price);
     if (price) product.price = price;
+
+    const originalPrice = await extractText(page, ...selectors.originalPrice);
+    if (price) product.originalPrice = originalPrice;
     
     // 提取评分
     const rating = await extractText(page, ...selectors.rating);
@@ -58,7 +66,7 @@ async function extractOttoData(page: Page, product: ProductData = {} as ProductD
     if (reviews) product.reviews = reviews;
     
     log.info(`✓ 成功提取商品数据:`, {
-      url: product.url || page.url(),
+      brand: product.brand || 'N/A',
       price: product.price || 'N/A',
       rating: product.rating || 'N/A',
       reviews: product.reviews || 'N/A'