如何抓取 Movoto：房地产网页抓取指南

from playwright.sync_api import sync_playwright

def scrape_movoto():
    with sync_playwright() as p:
        # 使用可见浏览器启动有助于绕过简单的机器人检查
        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()
        
        # 导航到特定城市的搜索页面
        page.goto('https://www.movoto.com/houston-tx/', wait_until='networkidle')
        
        # 等待房产卡片渲染
        page.wait_for_selector('.property-card')
        
        cards = page.query_selector_all('.property-card')
        for card in cards:
            price_el = card.query_selector('.price')
            if price_el:
                print(f'价格已找到: {price_el.inner_text()}')
        
        browser.close()

scrape_movoto()

import scrapy

class MovotoSpider(scrapy.Spider):
    name = 'movoto'
    start_urls = ['https://www.movoto.com/search/']
    
    # Scrapy 需要配合用于 Cloudflare 的中间件或 JS 渲染服务
    def parse(self, response):
        for card in response.css('.property-card'):
            yield {
                'price': card.css('.price::text').get(),
                'address': card.css('.address::text').get(),
                'beds': card.css('.beds::text').get()
            }
        
        # 简单的分页处理
        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();
  
  // 模拟真实用户浏览器会话
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  
  await page.goto('https://www.movoto.com/miami-fl/', { waitUntil: 'networkidle2' });
  
  // 提取房产数据
  const propertyData = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.property-card'));
    return cards.map(c => ({
      price: c.querySelector('.price')?.innerText,
      details: c.querySelector('.property-stats')?.innerText
    }));
  });

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