如何爬取 BetaList | BetaList 网页抓取指南

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # 启动真实浏览器以处理 JavaScript 和防机器人机制
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://betalist.com/', wait_until='networkidle')

        # 向下滚动以触发懒加载
        page.evaluate('window.scrollTo(0, document.body.scrollHeight)')
        page.wait_for_timeout(2000)

        # 提取初创企业数据
        startups = page.query_selector_all('.startupCard')
        for item in startups:
            name = item.query_selector('.startupCard__name').inner_text()
            tagline = item.query_selector('.startupCard__tagline').inner_text()
            print({'startup': name.strip(), 'tagline': tagline.strip()})

        browser.close()

run()

import scrapy

class BetalistSpider(scrapy.Spider):
    name = 'betalist_spider'
    start_urls = ['https://betalist.com/topics/ai']

    def parse(self, response):
        # Scrapy 速度很快，但可能需要针对 Cloudflare 的中间件
        for startup in response.css('.startupCard'):
            yield {
                'name': startup.css('.startupCard__name::text').get().strip(),
                'tagline': startup.css('.startupCard__tagline::text').get().strip(),
                'link': response.urljoin(startup.css('a::attr(href)').get())
            }

        # 处理简单的数字分页
        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();
  
  // 模拟真实用户浏览器以避免立即被检测
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/110.0.0.0 Safari/537.36');
  await page.goto('https://betalist.com/');

  // 等待内容通过 JS 渲染
  await page.waitForSelector('.startupCard');

  const results = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.startupCard'));
    return cards.map(c => ({
      title: c.querySelector('.startupCard__name').innerText.trim(),
      description: c.querySelector('.startupCard__tagline').innerText.trim()
    }));
  });

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