Coinalpha.appのスクレイピング方法 | 仮想通貨トークン上場スクレイパーガイド

import asyncio
from playwright.async_api import async_playwright

async def scrape_coinalpha_dynamic():
    async with async_playwright() as p:
        # ステルス設定を推奨してブラウザを起動
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        
        # New Born セクションへ移動
        await page.goto('https://coinalpha.app/new-born', wait_until='networkidle')
        
        # リストコンテナがロードされるのを待機
        await page.wait_for_selector('.token-card')
        
        tokens = await page.query_selector_all('.token-card')
        for token in tokens:
            name = await (await token.query_selector('.name')).inner_text()
            ca = await token.get_attribute('data-address')
            print(f'Token: {name} | CA: {ca}')
            
        await browser.close()

asyncio.run(scrape_coinalpha_dynamic())

import scrapy

class CoinalphaSpider(scrapy.Spider):
    name = 'coinalpha_spider'
    start_urls = ['https://coinalpha.app/']

    def parse(self, response):
        # CoinAlphaのJSを処理するにはミドルウェア（scrapy-playwrightなど）が必要です
        for project in response.css('.token-row'):
            yield {
                'name': project.css('.token-title::text').get(),
                'symbol': project.css('.symbol::text').get(),
                'votes': project.css('.vote-count::text').get(),
                'url': response.urljoin(project.css('a::attr(href)').get())
            }

        # ページネーションのロジック
        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();
  
  // 実在のブラウザを模倣するために User-Agent を設定
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36');
  
  await page.goto('https://coinalpha.app/', { waitUntil: 'networkidle2' });
  
  const data = await page.evaluate(() => {
    const rows = Array.from(document.querySelectorAll('.token-list-row'));
    return rows.map(row => ({
      name: row.querySelector('.token-name')?.innerText.trim(),
      votes: row.querySelector('.votes')?.innerText.trim()
    }));
  });

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