如何抓取 Geolocaux | Geolocaux 网页抓取指南

from playwright.sync_api import sync_playwright

def run_scraper():
    with sync_playwright() as p:
        # 启动浏览器并设置法国区域设置以模拟本地用户
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(locale='fr-FR')
        page = context.new_page()
        
        page.goto('https://www.geolocaux.com/location/bureau/')
        
        # 等待 JS 渲染的房源文章加载
        page.wait_for_selector('article')
        
        # 提取标题和价格
        properties = page.query_selector_all('article')
        for prop in properties:
            title = prop.query_selector('h3').inner_text()
            print(f'找到房产: {title}')
            
        browser.close()

run_scraper()

import scrapy

class GeolocauxSpider(scrapy.Spider):
    name = 'geolocaux'
    start_urls = ['https://www.geolocaux.com/location/bureau/']

    def parse(self, response):
        # 遍历房源容器
        for listing in response.css('article'):
            yield {
                'title': listing.css('h3::text').get(),
                'price': listing.css('.price::text').get(),
                'area': listing.css('.surface::text').get(),
            }

        # 通过查找“下一页”按钮处理分页
        next_page = response.css('a.pagination__next::attr(href)').get()
        if next_page is not None:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // 设置视口以触发正确的响应式布局
  await page.setViewport({ width: 1280, height: 800 });
  
  await page.goto('https://www.geolocaux.com/location/bureau/', { waitUntil: 'networkidle2' });

  const listings = await page.evaluate(() => {
    const data = [];
    document.querySelectorAll('article h3').forEach(el => {
      data.push({
        title: el.innerText.trim()
      });
    });
    return data;
  });

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