JWB Rental Homesのスクレイピング方法：不動産データ抽出ガイド

import asyncio
from playwright.async_api import async_playwright

async def scrape_jwb():
    async with async_playwright() as p:
        # JavaScriptサポート付きでブラウザを起動
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        
        # 検索結果ページに移動
        await page.goto('https://www.jwbrentalhomes.com/houses-for-rent/')
        
        # 物件グリッドが動的にロードされるのを待機
        await page.wait_for_selector('h4')
        
        # 住所と価格データを抽出
        properties = await page.query_selector_all('div.property-item')
        for prop in properties:
            title = await prop.query_selector('h4')
            address = await title.inner_text()
            print(f'Listing: {address.strip()}')
        
        await browser.close()

asyncio.run(scrape_jwb())

import scrapy

class JwbSpider(scrapy.Spider):
    name = 'jwb_spider'
    start_urls = ['https://www.jwbrentalhomes.com/houses-for-rent/']

    def parse(self, response):
        # 物件コンテナをループ処理
        for listing in response.css('div.property-item'):
            yield {
                'address': listing.css('h4 a::text').get(),
                'link': response.urljoin(listing.css('h4 a::attr(href)').get()),
                'price': listing.css('.rent-amount::text').get(),
                'beds': listing.css('.beds::text').get()
            }

        # シンプルなページネーション処理
        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();
  
  // JWBに移動し、ネットワークがアイドル状態になるまで待機
  await page.goto('https://www.jwbrentalhomes.com/houses-for-rent/', { waitUntil: 'networkidle2' });

  const listings = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('h4'));
    return items.map(item => ({
      address: item.innerText.trim(),
      url: item.querySelector('a')?.href
    }));
  });

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