python爬虫基础封装函数

# 导入包，模块
from urllib import request, parse
from urllib.error import HTTPError, URLError
#保存cookie
from http import cookiejar

#对于有登录是  所将用户记录下来 ，  
class session(object):
    def __init__(self):
        cookie_object = cookiejar.CookieJar()
        #handler  对应着一个操作
        handler = request.HTTPCookueProcessor(cookie_object)
        #调用handler内部的一个函数，存储到cookie  object
        self.opener = request.build_opener(handler)
   
    # get请求时
    def get(self, url, headers=None):
        return get(url, headers, self.opener)
    #post请求时
    def post(self, url, from, headers=None):
        return post(url, form, headers, self.opener)

# 定义函数
# get方法
def get(url, headers=None):
    return urlrequests(url, headers=headers)


# post方法
def post(url, form, headers=None):
    return urlrequests(url,form, headers = headers)

    # 进行封装函数
    # 1.传入url
    # 2.user_agent
    # 3.headers
    # 4.定义Request
    # 5.urlopen
    # 6.返回byte数组

def urlrequests(url, form =None, headers=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:
                # POST  转换成str
                from_str = parse.urlencode(
                form)
                # 转换成bytes
                form_bytes = form_str.encode('utf-8')
                req = request.Request(url, data=form_bytes, headers=headers)
            else:
            # GET
                req = request.Request(url, headers=headers)

            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__':
#百度翻译
    # url = 'http://fanyi.baidu.com/sug'
    # form = {
    # 'kw': '翻译的内容'
    # }
    # #post访问
    # html_bytes = post(url, form=form)
    # print(html_bytes)

    url = 'http://www.baidu.com'
    # get访问
    html_byte = get(url)
    print(html_byte)