Python爬虫基础 Day2 requests模块案例 简易网页采集器

使用 UA检测反扒机制所对应的 UA伪装反反爬伪装来实现

1.指定url

2.发起请求

3.获取响应数据

4.存储数据

import requests
#1.指定url
if __name__=='__main__':
    url = 'https://www.sogou.com/web'
    headers ={
            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36'

    }
    keyword = input('请输入查找内容：')
    params = {
            'query':keyword
    }
    #2.发送请求

    response = requests.get(url=url,params=params,headers=headers)

    #3.获取响应数据
    data = response.text


    #4.保存数据
    fileName = keyword+'.html'
    with open(fileName,'w',encoding='utf-8') as f:
        f.write(data)
    print(fileName+'下载完成')