spider(爬虫)简易网页采集器

通过输入指定的关键字搜索网页中的信息,啥也不说直接上代码

import requests
def spider():
    headers= {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.76'

    }
    url = "https://www.sogou.com/web"
    kw = input('enter a word')
    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 f:
        f.write(page_text)
    print(fileName,"保存成功!!")

if __name__ == '__main__':
    spider()

 

你可能感兴趣的:(爬虫)