如何爬取 Kleinanzeigen | 德国最大的分类广告市场

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0', locale='de-DE')
        page = context.new_page()
        
        # 导航至列表页面
        page.goto('https://www.kleinanzeigen.de/s-anzeige/beispiel', wait_until='networkidle')
        
        # 提取详情
        title = page.locator('h1#viewad-title').inner_text()
        price = page.locator('#viewad-price').inner_text()
        
        print({'title': title.strip(), 'price': price.strip()})
        browser.close()

run()

import scrapy

class KleinanzeigenSpider(scrapy.Spider):
    name = 'kleinanzeigen'
    start_urls = ['https://www.kleinanzeigen.de/s-berlin/c0-l3331']
    
    def parse(self, response):
        for ad in response.css('article.aditem'):
            yield {
                'title': ad.css('.aditem-main--title-line a::text').get(),
                'price': ad.css('.aditem-main--middle--price-shipping--price::text').get(),
                'location': ad.css('.aditem-main--top--left::text').get()
            }
        
        # 翻页处理
        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();
  const page = await browser.newPage();
  // 设置语言以匹配本地用户
  await page.setExtraHTTPHeaders({'Accept-Language': 'de-DE'});

  await page.goto('https://www.kleinanzeigen.de/s-berlin/c0-l3331');
  const ads = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.aditem')).map(el => ({
      title: el.querySelector('.aditem-main--title-line a')?.innerText,
      price: el.querySelector('.aditem-main--middle--price-shipping--price')?.innerText
    }));
  });

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