AssetColumnのスクレイピング方法：不動産と卸売（Wholesale）リードの獲得

import asyncio
from playwright.async_api import async_playwright

async def run():
    async with async_playwright() as p:
        # ヘッドレスモードでブラウザを起動
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        
        # ターゲットページに移動し、リスティングの読み込みを待機
        await page.goto('https://www.assetcolumn.com/for-sale')
        await page.wait_for_selector('h3')
        
        # リスティング要素を選択
        elements = await page.query_selector_all('div.latest-houses-item')
        for el in elements:
            title = await (await el.query_selector('h3')).inner_text()
            price = await (await el.query_selector('b')).inner_text()
            print(f'Found: {title} at {price}')
            
        await browser.close()

asyncio.run(run())

import scrapy

class AssetColumnSpider(scrapy.Spider):
    name = 'assetcolumn'
    start_urls = ['https://www.assetcolumn.com/for-sale']

    def parse(self, response):
        # CSSセレクターを使用して物件カードをループ処理
        for property_card in response.css('.latest-houses-item'):
            yield {
                'title': property_card.css('h3 a::text').get().strip(),
                'asking_price': property_card.xpath('.//b/text()').get(),
                'url': response.urljoin(property_card.css('h3 a::attr(href)').get()),
                'arv': property_card.xpath('//text()[contains(., "ARV")]/following-sibling::text()').get()
            }
        
        # シンプルなページネーションロジック
        next_page = response.css('a.next::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();
  
  // 基本的な検知を回避するために実際のUser-Agentを模倣
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  await page.goto('https://www.assetcolumn.com/for-sale', { waitUntil: 'networkidle2' });

  const data = await page.evaluate(() => {
    // DOMから直接データを抽出
    return Array.from(document.querySelectorAll('.latest-houses-item')).map(item => ({
      title: item.querySelector('h3')?.innerText.trim(),
      price: item.querySelector('b')?.innerText.trim()
    }));
  });

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