j简单的python爬虫封装

#导包
from urllib import request
from urllib.error import HTTPError,URLError

#传入url
def url_request(url,headers = None):
    #传入user_agent
    user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    headers = {
        'User-Agent':user_agent
    }
    #定义html_bytrs  二进制
    html_bytrs = b''
    try:
        #定义Request
        req = request.Request(url,headers=headers)
        resp = request.urlopen(req)
        html_bytrs = resp.read()
    #遇到什么样的错误打印什么错误
    except HTTPError as e:
        print(e)
    except URLError as e:
        print(e)
    #返回byte数组
    return html_bytrs

if __name__ == '__main__':
    html_bytes = url_request('http://www.xicidaili.com')
    print(html_bytes.decode('utf-8'))