Python爬虫：汽车之家爬虫（完整代码）

import requests
from lxml import etree
import csv
 
def get_car_info(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36',
    }
    response = requests.get(url, headers=headers)
    response.encoding = 'utf-8'
    html = etree.HTML(response.text)
    return html
 
def parse_car_info(html):
    # 汽车名称
    name = html.xpath('//div[@class="car-intro-cont"]/h1/text()')[0]
    # 汽车价格
    price = html.xpath('//div[@class="car-price-cont"]/p[@class="car-price-num"]/text()')[0]
    # 汽车图片
    image = html.xpath('//div[@class="car-intro-img"]/img/@src')[0]
    # 汽车参数
    parameters = html.xpath('//div[@class="car-param-cont"]/p/text()')
    return {
        'name': name,
        'price': price,
        'image': image,
        'parameters': parameters
    }
 
def save_car_info(car_info, file_name):
    with open(file_name, 'w', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        writer.writerow(['name', 'price', 'image', 'parameters'])
        writer.writerow([car_info['name'], car_info['price'], car_info['image'], ','.join(car_info['parameters'])])
 
def main():
    url = 'https://www.autohome.com.cn/156148/#pvareaid=201571'
    html = get_car_info(url)
    car_info = parse_car_info(html)
    save_car_info(car_info, 'car_info.csv')
 
if __name__ == '__main__':
    main()

这段代码实现了汽车之家网站特定汽车信息的抓取，并将其保存到CSV文件中。代码首先定义了获取网页、解析网页以及保存数据的函数。然后在main函数中，我们调用这些函数，完成数据抓取和保存的流程。在实际应用中，你需要根据目标网站的具体结构调整XPath表达式。