Carwow 스크레이핑 방법: 중고차 데이터 및 가격 추출 가이드

import asyncio
from playwright.async_api import async_playwright

async def run():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = await browser.new_page()
        await page.goto('https://www.carwow.co.uk/used-cars')
        # Wait for listings to render via JS
        await page.wait_for_selector('.stock-card')
        # Scroll to load dynamic data
        await page.evaluate('window.scrollTo(0, document.body.scrollHeight)')
        cars = await page.query_selector_all('.stock-card')
        for car in cars:
            name = await (await car.query_selector('h3')).inner_text()
            print(f'Found: {name}')
        await browser.close()

asyncio.run(run())

import scrapy

class CarwowSpider(scrapy.Spider):
    name = 'carwow'
    start_urls = ['https://www.carwow.co.uk/used-cars']

    def parse(self, response):
        for car in response.css('div.stock-card'):
            yield {
                'title': car.css('h3::text').get(),
                'price': car.css('.price-value::text').get(),
                'link': response.urljoin(car.css('a::attr(href)').get())
            }
        # Handle pagination
        next_page = response.css('a.next-page::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer-extra');
const StealthPlugin = require('puppeteer-extra-plugin-stealth');
puppeteer.use(StealthPlugin());

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.goto('https://www.carwow.co.uk/used-cars', { waitUntil: 'networkidle2' });
  const data = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.stock-card')).map(el => ({
      title: el.querySelector('h3').innerText,
      price: el.querySelector('.price').innerText
    }));
  });
  console.log(data);
  await browser.close();
})();