如何抓取 CoinBrain：加密数据提取指南

from playwright.sync_api import sync_playwright

def run(playwright):
    browser = playwright.chromium.launch(headless=True)
    context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36")
    page = context.new_page()
    page.goto("https://coinbrain.com/trending")
    
    # 等待动态 token 元素出现
    page.wait_for_selector('.coin-row')
    
    coins = page.query_selector_all('.coin-row')
    for coin in coins[:5]:
        name = coin.query_selector('.coin-name').inner_text()
        price = coin.query_selector('.coin-price').inner_text()
        print(f'Token: {name}, Price: {price}')
    
    browser.close()

with sync_playwright() as pw:
    run(pw)

import scrapy

class CoinbrainSpider(scrapy.Spider):
    name = 'coinbrain_spider'
    start_urls = ['https://coinbrain.com/new-coins']

    def parse(self, response):
        # 建议使用 Scrapy-Playwright 中间件进行 JS 执行
        for coin in response.css('.coin-list-item'):
            yield {
                'name': coin.css('.name::text').get(),
                'symbol': coin.css('.symbol::text').get(),
                'price': coin.css('.price::text').get(),
            }
        
        next_page = response.css('a.next-page::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();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  await page.goto('https://coinbrain.com/trending');

  // 等待 React 激活并加载数据
  await page.waitForSelector('.token-list');

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

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