Progress Residential 웹사이트 스크래핑 방법

from playwright.sync_api import sync_playwright

def scrape_progress():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = context.new_page()
        page.goto('https://rentprogress.com/houses-for-rent/search', wait_until='networkidle')
        
        # 동적 콘텐츠가 로드될 때까지 대기
        page.wait_for_selector('.property-card')
        
        items = page.query_selector_all('.property-card')
        results = []
        for item in items:
            results.append({
                'address': item.query_selector('.address-line').inner_text(),
                'rent': item.query_selector('.rent-amount').inner_text(),
                'specs': item.query_selector('.specs').inner_text()
            })
        print(results)
        browser.close()

if __name__ == '__main__':
    scrape_progress()

import scrapy

class ProgressSpider(scrapy.Spider):
    name = 'progress_spider'
    start_urls = ['https://rentprogress.com/houses-for-rent/search']
    
    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
        'DOWNLOAD_DELAY': 2,
        'ROBOTSTXT_OBEY': False
    }

    def parse(self, response):
        for property in response.css('.property-card-container'):
            yield {
                'address': property.css('.prop-address::text').get(),
                'price': property.css('.prop-price::text').get(),
                'sqft': property.css('.prop-sqft::text').get(),
            }
        
        next_page = response.css('a.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.setViewport({ width: 1280, height: 800 });
  await page.setUserAgent('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36');

  await page.goto('https://rentprogress.com/houses-for-rent/search', { waitUntil: 'networkidle2' });

  const propertyData = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.property-card'));
    return cards.map(card => ({
      location: card.querySelector('.address-title')?.innerText.trim(),
      monthlyRent: card.querySelector('.rent-val')?.innerText.trim(),
      bedrooms: card.querySelector('.bed-count')?.innerText.trim()
    }));
  });

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