爬虫基础：函数封装(更新一)

# 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请求的封装函数
def get(url, headers=None):

    # 内层函数urlrequests函数的返回值返回给外层函数get
    return urlrequests(url, headers=headers)
 
 
#post请求的封装函数
def post(url, form, headers=None):
    return urlrequests(url,form, headers = headers)
 
    
 
def urlrequests(url, form =None, headers=None):

        #传入url
     user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
        #如果用户需要自行传入headers，则需要覆盖之前的headers

        if headers == None:

            #定义headers
            headers = {
                'User-Agent': user_agent
            }

        #定义变量（容器），默认二进制写入
        html_bytes = b''
        try:

            #判断是post请求还是get请求
            if form:
                # POST  转换成str
                from_str = parse.urlencode( form)
                # 转换成bytes
                form_bytes = form_str.encode('utf-8')

                # 定义Request
                req = request.Request(url, data=form_bytes, headers=headers)
            else:
            # get
                req = request.Request(url, headers=headers)
            #添加 urlopen方法
            response = request.urlopen(req)
            html_bytes = response.read()
 
        except HTTPError as e:
            print(e)
        except URLError as e:
            print(e)

        #返回bytes数组
        return html_bytes

if __name__ == '__main__':
##post
# url = 'http://fanyi.baidu.com/sug'
# form = {
# 'kw':'蓝色'
# }
# html_bytes = post(url,form=form)
# print(html_bytes) #返回结果：b'{"errno":0,"data":[{"k":"\\u84dd\\u8272","v":"[l\\u00e1n s\\u00e8] blue; blueness; blove;"},{"k":"\\u84dd\\u8272\\u7684","v":"blue; blove;"},{"k":"\\u84dd\\u8272\\u5996\\u59ec","v":"blue enchantress(\\u4e00\\u79cd\\u82b1\\u540d\\uff0c\\u53c8\\u79f0\\u84dd\\u8272\\u73ab\\u7470);"},{"k":"\\u84dd\\u8272\\u706b\\u7130","v":"[\\u533b]blue flame;"},{"k":"\\u84dd\\u8272\\u8309\\u8389","v":"[\\u7535\\u5f71]Blue Jasmine;"}]}

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