python入门爬虫实例(含代码)

准备工作

(1)导入requeste库,需要下载

(2)获取url

(3)查找User-Agent(请求载体的身份标识符),把它当成headers,避免反爬

(4)把获取到的的数据存储起来

import requests
if __name__ == "__main__":
    url = "https://www.sogou.com/web"
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.0.3161 SLBChan/105"
    }              #从网页中获取，避免识别到是爬虫
    kw = input("目标")
    param = {
        "query": kw        #控制搜索内容
    }
    #requeste.get()拿response接收
    response = requests.get(url=url, params=param, headers=headers) 
    r = response.text
    fileName = kw+".html"
    # encoding="utf-8"避免乱码
    with open(fileName, 'w', encoding="utf-8") as fp:
        fp.write(r)
    print(fileName, "保存成功")