CNTOKEN.io をスクレイピングする方法 | 中国語圏の暗号資産インデックス Web スクレイパー

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://cntoken.io/coins')
        # テーブルの読み込みを待機
        page.wait_for_selector('.coin-list-table')
        tokens = page.query_selector_all('.coin-list-row')
        results = []
        for token in tokens[:10]:
            name = token.query_selector('.name').inner_text()
            price = token.query_selector('.price').inner_text()
            results.append({'name': name, 'price': price})
        print(results)
        browser.close()

run()

import scrapy

class CntokenSpider(scrapy.Spider):
    name = 'cntoken_spider'
    start_urls = ['https://cntoken.io/coins']
    
    def parse(self, response):
        for row in response.css('.coin-list-row'):
            yield {
                'name': row.css('.name::text').get().strip(),
                'symbol': row.css('.symbol::text').get().strip(),
                'price': row.css('.price::text').get().strip(),
                'network': row.css('.network-label::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();
  const page = await browser.newPage();
  await page.goto('https://cntoken.io/coins', { waitUntil: 'networkidle2' });
  
  const data = await page.evaluate(() => {
    const rows = Array.from(document.querySelectorAll('.coin-list-row'));
    return rows.map(row => ({
      name: row.querySelector('.name')?.innerText.trim(),
      symbol: row.querySelector('.symbol')?.innerText.trim(),
      price: row.querySelector('.price')?.innerText.trim()
    }));
  });

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