Rent.comをスクレイピングする方法：不動産データ抽出ガイド

import asyncio
from playwright.async_api import async_playwright

async def scrape_rent_data():
    async with async_playwright() as p:
        # Rent.comにはステルスアプローチが必要
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = await context.new_page()
        
        # 特定の都市のリスティングページへ遷移
        await page.goto('https://www.rent.com/california/los-angeles-apartments')
        
        # 動的な物件カードがDOMに表示されるまで待機
        await page.wait_for_selector('[data-tag="listing-card"]')
        
        listings = await page.query_selector_all('[data-tag="listing-card"]')
        for item in listings:
            title_el = await item.query_selector('[data-tag="property-title"]')
            price_el = await item.query_selector('[data-tag="property-price"]')
            if title_el and price_el:
                print(f'{await title_el.inner_text()} - {await price_el.inner_text()}')
        
        await browser.close()

asyncio.run(scrape_rent_data())

import scrapy

class RentDotComSpider(scrapy.Spider):
    name = 'rent_spider'
    start_urls = ['https://www.rent.com/texas/austin-apartments']

    def parse(self, response):
        # data-tag属性を使用して物件データを抽出
        for listing in response.css('[data-tag="listing-card"]'):
            yield {
                'name': listing.css('[data-tag="property-title"]::text').get(),
                'price': listing.css('[data-tag="property-price"]::text').get(),
                'address': listing.css('[data-tag="property-address"]::text').get()
            }
        
        # Rent.comの基本的なページネーション処理
        next_page = response.css('a[data-tag="pagination-next"]::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer-extra');
const StealthPlugin = require('puppeteer-extra-plugin-stealth');
puppeteer.use(StealthPlugin());

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  // ネットワークがアイドル状態になるまでRent.comのページへ遷移
  await page.goto('https://www.rent.com/florida/miami-apartments', { waitUntil: 'networkidle2' });
  
  // 抽出前にリスティングが読み込まれていることを確認
  await page.waitForSelector('[data-tag="listing-card"]');
  
  const properties = await page.evaluate(() => {
    const results = [];
    document.querySelectorAll('[data-tag="listing-card"]').forEach(el => {
      results.push({
        title: el.querySelector('[data-tag="property-title"]')?.innerText,
        price: el.querySelector('[data-tag="property-price"]')?.innerText
      });
    });
    return results;
  });

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