完善get和post方式爬取网页 增加cookie可模拟登录

from urllib import request,parse
from urllib.error import HTTPError,URLError
from http import cookiejar

class session(object):

    def __init__(self):
        #保存cookie
        cookie_object = cookiejar.CookieJar()
        #handler 对应着操作
        handler = request.HTTPCookieProcessor(cookie_object)
        #调用handler内部的函数 存储到cookie object
        self.opener = request.build_opener(handler)

    #定义get方法传递opener
    def get(self,url,headers=None):
        return get(url,headers,self.opener)

    #定义post方法传递opener
    def post(self,url,form,headers=None):
        return post(url,form,headers,self.opener)

#get方式      
def get(url,headers=None,opener=None):
    return urlrequest(url,headers=headers,opener=opener)

#post方式
def post(url,form,headers=None,opener=None):
    return urlrequest(url,form,headers=headers,opener=opener)

def urlrequest(url,form=None,headers=None,opener=None):
    user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    if headers==None:
        headers = {
            'User-Agent':user_agent
        }
    html_bytes = b''
    try:
        if form:
            form_str = parse.urlencode(form,encoding='utf-8')
            form_bytes = form_str.encode('utf-8')
            req = request.Request(url,data=form_bytes,headers=headers)
        else:
            req = request.Request(url,headers=headers)
        if opener:
            response = opener.open(req)
        else:
            response = request.urlopen(req)
        html_bytes = response.read()
    except HTTPError as e:
        print(e)
    except URLError as e:
        print(e)

    return html_bytes

if __name__ == '__main__':
    url = 'http://www.baidu.com'
    html_byte = get(url)
    print(html_byte)