如何抓取 Car.info | 车辆数据与估值提取指南

import asyncio
from playwright.async_api import async_playwright

async def scrape_car_specs():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        await page.goto('https://www.car.info/en-se/volvo/v60/v60-2023-22874136')
        # 等待动态技术参数表加载
        await page.wait_for_selector('.tech-spec-table')
        specs = await page.query_selector_all('.tech-spec-row')
        for spec in specs:
            label = await spec.query_selector('.label')
            value = await spec.query_selector('.value')
            if label and value:
                print(f'{await label.inner_text()}: {await value.inner_text()}')
        await browser.close()

asyncio.run(scrape_car_specs())

import scrapy

class CarInfoSpider(scrapy.Spider):
    name = 'car_spider'
    start_urls = ['https://www.car.info/en-se/volvo/v60']

    def parse(self, response):
        for car in response.css('.car-listing'):
            yield {
                'model': car.css('.model-name::text').get(),
                'year': car.css('.model-year::text').get(),
                'valuation': car.css('.valuation-range::text').get(),
            }
        # 分页处理
        next_page = response.css('a.next-btn::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();
  await page.goto('https://www.car.info/en-se/spots');
  await page.waitForSelector('.spot-item');
  const data = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.spot-item')).map(item => ({
      car: item.querySelector('.car-name')?.innerText,
      plate: item.querySelector('.license-plate')?.innerText,
      location: item.querySelector('.spot-location')?.innerText
    }));
  });
  console.log(data);
  await browser.close();
})();