whatsmydns.netをスクレイピングする方法：DNSデータの完全ガイド

from playwright.sync_api import sync_playwright

def scrape_whatsmydns():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # ハッシュベースのURLを使用して、特定のDNSルックアップをトリガーします
        page.goto('https://www.whatsmydns.net/#A/google.com')
        
        # 結果テーブルにデータが入るのを待ちます
        page.wait_for_selector('.results-table tr', timeout=15000)
        
        # 結果を抽出します
        rows = page.query_selector_all('.results-table tr')
        for row in rows:
            location = row.query_selector('.location').inner_text()
            result_val = row.query_selector('.value').inner_text()
            print(f'[{location}] Resolved to: {result_val}')
            
        browser.close()

scrape_whatsmydns()

import scrapy
from scrapy_playwright.page import PageMethod

class DNSPropagationSpider(scrapy.Spider):
    name = 'dns_spider'
    
    def start_requests(self):
        # Scrapy-PlaywrightがJSレンダリングを処理します
        yield scrapy.Request(
            'https://www.whatsmydns.net/#A/example.com',
            meta={
                'playwright': True,
                'playwright_page_methods': [
                    PageMethod('wait_for_selector', '.results-table tr')
                ]
            }
        )

    def parse(self, response):
        # Playwright経由で抽出されたテーブル行を反復処理します
        for row in response.css('.results-table tr'):
            yield {
                'location': row.css('.location::text').get(),
                'result': row.css('.value::text').get()
            }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // DNSチェックURLに直接移動します
  await page.goto('https://www.whatsmydns.net/#MX/microsoft.com', { waitUntil: 'networkidle2' });
  
  // 動的なサーバー行が読み込まれるのを待ちます
  await page.waitForSelector('.results-table tr');

  const data = await page.evaluate(() => {
    const rows = Array.from(document.querySelectorAll('.results-table tr'));
    return rows.map(row => ({
      location: row.querySelector('.location')?.innerText.trim(),
      value: row.querySelector('.value')?.innerText.trim()
    }));
  });

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