如何爬取 StubHub：终极网页爬虫指南

from playwright.sync_api import sync_playwright

def scrape_stubhub():
    with sync_playwright() as p:
        # 启动有头或无头浏览器
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36')
        page = context.new_page()
        
        # 导航到特定活动页面
        page.goto('https://www.stubhub.com/concert-tickets/')
        
        # 等待动态门票列表加载到 DOM 中
        page.wait_for_selector('.event-card', timeout=10000)
        
        # 使用 locator 提取数据
        titles = page.locator('.event-card-title').all_inner_texts()
        for title in titles:
            print(title)
            
        browser.close()

if __name__ == '__main__':
    scrape_stubhub()

import scrapy

class StubHubSpider(scrapy.Spider):
    name = 'stubhub_spider'
    start_urls = ['https://www.stubhub.com/search']

    def parse(self, response):
        # StubHub 的数据通常位于 JSON 脚本标签内或通过 JS 渲染
        # 此示例假设使用标准 CSS 选择器进行演示
        for event in response.css('.event-item-container'):
            yield {
                'name': event.css('.event-title::text').get(),
                'price': event.css('.price-amount::text').get(),
                'location': event.css('.venue-info::text').get()
            }

        # 通过查找“下一页”按钮处理分页
        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({ headless: true });
  const page = await browser.newPage();
  
  // 设置真实的 User Agent
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36');

  try {
    await page.goto('https://www.stubhub.com', { waitUntil: 'networkidle2' });
    
    // 等待 React 渲染列表
    await page.waitForSelector('.event-card');

    const data = await page.evaluate(() => {
      const items = Array.from(document.querySelectorAll('.event-card'));
      return items.map(item => ({
        title: item.querySelector('.event-title-class')?.innerText,
        price: item.querySelector('.price-class')?.innerText
      }));
    });

    console.log(data);
  } catch (err) {
    console.error('爬取过程中出错:', err);
  } finally {
    await browser.close();
  }
})();