RE/MAX (remax.com) 부동산 매물 데이터를 스크래핑하는 방법

import asyncio
from playwright.async_api import async_playwright

async def run():
    async with async_playwright() as p:
        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 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
        )
        page = await context.new_page()
        
        print('Navigating to RE/MAX...')
        await page.goto('https://www.remax.com/homes-for-sale/co/denver/city/0820000', wait_until='networkidle')
        
        # Wait for property list to load
        await page.wait_for_selector('.property-card')
        
        listings = await page.query_selector_all('.property-card')
        for listing in listings:
            price = await listing.query_selector('[data-test="property-price"]')
            address = await listing.query_selector('[data-test="property-address"]')
            if price and address:
                print(f'Price: {await price.inner_text()} | Address: {await address.inner_text()}')
        
        await browser.close()

asyncio.run(run())

import scrapy

class RemaxSpider(scrapy.Spider):
    name = 'remax_spider'
    allowed_domains = ['remax.com']
    start_urls = ['https://www.remax.com/homes-for-sale/co/denver/city/0820000']

    def parse(self, response):
        for listing in response.css('.property-card'):
            yield {
                'price': listing.css('[data-test="property-price"]::text').get(),
                'address': listing.css('[data-test="property-address"]::text').get(),
                'beds': listing.css('[data-test="property-beds"]::text').get(),
            }
        
        next_page = response.css('a[data-test="pagination-next"]::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36');
  
  await page.goto('https://www.remax.com/homes-for-sale/co/denver/city/0820000', { waitUntil: 'networkidle2' });
  
  const data = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.property-card'));
    return cards.map(card => ({
      price: card.querySelector('[data-test="property-price"]')?.innerText,
      address: card.querySelector('[data-test="property-address"]')?.innerText
    }));
  });

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