آموزش استخراج داده از Realtor.com | راهنمای جامع اسکرپینگ ۲۰۲۶

from playwright.sync_api import sync_playwright

def scrape_realtor():
    with sync_playwright() as p:
        # Launching with stealth-like settings
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) ...")
        page = context.new_page()
        
        print("Navigating to Realtor.com...")
        page.goto("https://www.realtor.com/realestateandhomes-search/Austin_TX", wait_until="networkidle")
        
        # Wait for property card selectors to load via JS
        page.wait_for_selector('div[data-testid="property-card"]')
        
        listings = page.query_selector_all('div[data-testid="property-card"]')
        for item in listings:
            price = item.query_selector('[data-label="pc-price"]').inner_text()
            address = item.query_selector('[data-label="pc-address"]').inner_text()
            print(f"Listing: {address} - Price: {price}")
            
        browser.close()

scrape_realtor()

import scrapy

class RealtorSpider(scrapy.Spider):
    name = 'realtor_spider'
    start_urls = ['https://www.realtor.com/realestateandhomes-search/Miami_FL']

    def parse(self, response):
        # Extracting data using CSS selectors
        for property in response.css('div[data-testid="property-card"]'):
            yield {
                'price': property.css('span[data-label="pc-price"]::text').get(),
                'address': property.css('div[data-label="pc-address"]::text').get(),
                'beds': property.css('li[data-label="pc-meta-beds"] span::text').get()
            }

        # Simple pagination handling
        next_page = response.css('a[aria-label="Go to 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({ headless: true });
  const page = await browser.newPage();
  
  // Set high-level headers to mimic a real user
  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');
  
  console.log('Visiting Realtor.com...');
  await page.goto('https://www.realtor.com/realestateandhomes-search/Chicago_IL', { waitUntil: 'domcontentloaded' });
  
  // Wait for the price elements to be visible
  await page.waitForSelector('.pc-price');
  
  const results = await page.evaluate(() => {
    const prices = Array.from(document.querySelectorAll('.pc-price'));
    return prices.map(p => p.innerText);
  });
  
  console.log('Extracted Prices:', results);
  await browser.close();
})();