爬虫基本样式

from urllib import request
from  urllib import parse

#拼接URL地址函数
def get_url(word):
    baseurl="https://www.baidu.com/s?"
    #编码+拼接
    parasm=parse.urlencode({"wd":word})#编码
    url=baseurl+parasm+"&usm=3&rsv_idx=2&rsv_page=1"#&usm=3&rsv_idx=2&rsv_page=1 PY百度请求百度安全验证的问题
    return url

#请求+保存
def write_html(url,word):
    headers={"User-Agent":"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)"}
    req=request.Request(url=url,headers=headers)#创建请求对象
    res=request.urlopen(req)#获取响应对象
    html=res.read().decode()

    filename=word+".html"
    with open(filename,"w",encoding="utf-8") as f:
        f.write(html)

if __name__ == '__main__':
    word=input("请输入你要查询的内容：")
    url=get_url(word)
    write_html(url,word)