python编程-数据爬取2

今天进行数据爬取的几个练习

1、简易网页采集器

import requests
if __name__ == '__main__':
#UA检测
    #UA伪装:让爬虫对应的请求载体身份标识伪装成某一款浏览器
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.0.10191 SLBChan/103'
    }
    url='https://www.sogou.com/web'
    kw=input('输入字段')
    param = {
        'query':kw
    }
    response=requests.get(url=url,params=param,headers=headers)
    page_text =response.text
    fileName =kw+'.html'
    with open(fileName, 'w', encoding='utf-8') as fp:
        fp.write(page_text)
    print('爬取数据完成')

显示效果