如何爬取 HP.com：产品与价格数据抓取技术指南

import asyncio
from playwright.async_api import async_playwright

async def scrape_hp():
    async with async_playwright() as p:
        # 爬取 HP 通常需要使用 stealth 模式或自定义 UA
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = await context.new_page()
        
        await page.goto('https://www.hp.com/us-en/shop/sitesearch?keyword=laptop')
        
        # 等待动态 React 元素渲染
        await page.wait_for_selector('.product-item')
        products = await page.query_selector_all('.product-item')
        
        for product in products:
            title_el = await product.query_selector('h5')
            price_el = await product.query_selector('.sale-price')
            title = await title_el.inner_text() if title_el else 'N/A'
            price = await price_el.inner_text() if price_el else 'N/A'
            print(f'Found: {title} | Price: {price}')
        
        await browser.close()

asyncio.run(scrape_hp())

import scrapy

class HpSpider(scrapy.Spider):
    name = 'hp_spider'
    start_urls = ['https://www.hp.com/us-en/shop/sitesearch?keyword=laptop']

    def parse(self, response):
        # Scrapy 本身无法渲染 JS；生产环境中请使用 scrapy-playwright 中间件
        for product in response.css('.product-item'):
            yield {
                'title': product.css('h5::text').get(),
                'price': product.css('.sale-price::text').get(),
                'sku': product.css('.sku-label::text').get()
            }
        # 分页逻辑
        next_page = response.css('a.next::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // 使用 networkidle2 确保大部分动态内容已加载
  await page.goto('https://www.hp.com/us-en/shop/sitesearch?keyword=laptop', { 
    waitUntil: 'networkidle2' 
  });

  const products = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('.product-item'));
    return items.map(item => ({
      name: item.querySelector('h5')?.innerText,
      price: item.querySelector('.sale-price')?.innerText
    }));
  });

  console.log(products);
  await browser.close();
})();