如何爬取 eBay | eBay 网页爬虫指南

from playwright.sync_api import sync_playwright

def scrape_ebay():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0...')
        page = context.new_page()
        
        # 导航至 eBay 搜索
        page.goto('https://www.ebay.com/sch/i.html?_nkw=laptop')
        
        # 等待列表加载
        page.wait_for_selector('.s-item__info')
        
        listings = page.locator('.s-item__info').all()
        for item in listings[:5]:
            title = item.locator('.s-item__title').inner_text()
            price = item.locator('.s-item__price').inner_text()
            print(f'产品: {title} - {price}')
        
        browser.close()

scrape_ebay()

import scrapy

class EbaySpider(scrapy.Spider):
    name = 'ebay'
    start_urls = ['https://www.ebay.com/sch/i.html?_nkw=camera']

    def parse(self, response):
        for listing in response.css('.s-item__info'):
            yield {
                'title': listing.css('.s-item__title span::text').get(),
                'price': listing.css('.s-item__price::text').get(),
                'condition': listing.css('.SECONDARY_INFO::text').get()
            }

        next_page = response.css('a.pagination__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();
  await page.setUserAgent('Mozilla/5.0...');
  
  await page.goto('https://www.ebay.com/sch/i.html?_nkw=watch');
  await page.waitForSelector('.s-item__info');

  const data = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.s-item__info')).map(el => ({
      title: el.querySelector('.s-item__title')?.innerText,
      price: el.querySelector('.s-item__price')?.innerText
    }));
  });

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