Redfinのスクレイピング方法：不動産データ抽出ガイド

from playwright.sync_api import sync_playwright

def scrape_redfin():
    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()
        
        # Navigate to a search result page
        page.goto('https://www.redfin.com/city/30756/GA/Atlanta')
        
        # Wait for listings to load dynamically
        page.wait_for_selector('.HomeCardContainer')
        
        # Extract data
        homes = page.query_selector_all('.HomeCardContainer')
        for home in homes:
            price = home.query_selector('.homecardV2Price').inner_text()
            address = home.query_selector('.homeAddressV2').inner_text()
            print({'address': address, 'price': price})
            
        browser.close()

scrape_redfin()

import scrapy

class RedfinSpider(scrapy.Spider):
    name = 'redfin'
    start_urls = ['https://www.redfin.com/city/30756/GA/Atlanta']

    def parse(self, response):
        for home in response.css('.HomeCardContainer'):
            yield {
                'price': home.css('.homecardV2Price::text').get(),
                'address': home.css('.homeAddressV2::text').get(),
                'details': home.css('.stats::text').getall(),
            }

        # Pagination handling
        next_page = response.css('a.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');

  await page.goto('https://www.redfin.com/city/30756/GA/Atlanta', { waitUntil: 'networkidle2' });

  const properties = await page.evaluate(() => {
    const results = [];
    document.querySelectorAll('.HomeCardContainer').forEach(card => {
      results.push({
        price: card.querySelector('.homecardV2Price')?.innerText,
        address: card.querySelector('.homeAddressV2')?.innerText
      });
    });
    return results;
  });

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