python学习Day06--编码

【主要内容】

1. is 和 == 区别
      id()函数
      == 判断两边的值
      is 判断内存地址
回顾编码:
    1. ASCII: 英文, 特殊字符, 数字, 8bit, 1byte
    2. GBK: 中文 16bit, 2byte. 兼容ASCII
    3. unicode:　万国码, 32bit 4byte. 兼容ASCII
    4. UTF-8: 长度可变的unicode. 英文:8bit, 欧洲:１６bit, 中文:24bit 3byte

    python2 只能用ASCII
    python3 有unicode, 默认的编码就是unicode
    内存里用的是unicode. 硬盘和网络传输用的是utf-8或者GBK



2. encode()  编码. 获取到的是编码之后的结果. bytes
3. decode()  解码. 把bytes编程我们熟悉的字符串

【代码】

1、is和==

# s = "alex 是 大 xx"
# abc = id(s)   # 得到内存地址
# print(abc)

# lst = ["大阳哥", "佳琪哥", "小花生", "燃哥"]
# print(id(lst))  # 就是一个内存地址. 毫无意义


# lst = ["周杰伦", "燃哥"]
# lst1 = ["周杰伦", "燃哥"]
# print(id(lst))
# print(id(lst1))

# s = "燃哥"
# s1 = "燃哥"
# # 小数据池. 会对字符串进行缓存, 为了节省内存
# print(id(s))
# print(id(s1))

# tu = ("燃哥", "周杰伦")
# tu1 = ("燃哥", "周杰伦")
# print(id(tu), id(tu1))

# dic = {"a": "b", "c":"d"}
# dic1 = {"a": "b", "c":"d"}
# print(id(dic), id(dic1))

# a = 10
# b = 10
# print(id(a), id(b))

# 布尔也有,
# a = True
# b = True
# print(id(a), id(b))

# -5
# a = 257
# b = 257
# print(id(a), id(b))

# a = "小威"
# b = "小威"
# print(id(a), id(b))

# 1. id() 查看内存地址
# 2. str 有小数据池的

# == is id
# == 判断. 左右两端是否相等和一致, 比较的是内容
# is 判断. 判断的是内存地址  id()的值来判断    内存地址

# lst = ["马化腾", "小威"]
# lst2 = ["马化腾", "小威"]
# print(lst == lst2)  # True
# print(lst is lst2)  # False


# s = "alex"
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
# print("1111111111")
#
# s2 = "alex"
# print(s == s2) # True
# print(s is s2)  # True. 小数据池

# s1 = "@akljflkasdjklfjkasdlfjklsdajfklsdajfklasdjkflasdjklfjsdaklfjsdakljfklasdjfklsdajfklsdajfklsdajklfsjadklfjsadklfjasdkljfklsdjfklsdjfklsdjfklsdjfklasdjfklasdjklfjasdklakljflkasdjklfjkasdlfjklsdajfklsdajfklasdjkflasdjklfjsdaklfjsdakljfklasdjfklsdajfklsdajfklsdajklfsjadklfjsadklfjasdkljfklsdjfklsdjfklsdjfklsdjfklasdjfklasdjklfjasdkl"
# s2 = "@akljflkasdjklfjkasdlfjklsdajfklsdajfklasdjkflasdjklfjsdaklfjsdakljfklasdjfklsdajfklsdajfklsdajklfsjadklfjsadklfjasdkljfklsdjfklsdjfklsdjfklsdjfklasdjfklasdjklfjasdklakljflkasdjklfjkasdlfjklsdajfklsdajfklasdjkflasdjklfjsdaklfjsdakljfklasdjfklsdajfklsdajfklsdajklfsjadklfjsadklfjasdkljfklsdjfklsdjfklsdjfklsdjfklasdjfklasdjklfjasdkl"
# print(id(s1), id(s2))
#
# s = "abc中def"
# print(s.title())

2、编码

# s = "alex马"
# 想要存储.必须进行编码

# encode() 编码之后的内容是bytes类型的数据

# 30个字节 10个字. 每个字3个字节
# b'\xe6\x9d\x8e\xe5\x98\x89\xe8\xaf\x9a\xe7\x9a\x84\xe5\x84\xbf\xe5\xad\x90\xe8\xa2\xab\xe7\xbb\x91\xe6\x9e\xb6\xe4\xba\x86'
# bs = s.encode("UTF-8")   # 把字符串编码成UTF-8的形式
# print(bs)

# 英文:编码之后的结果是英文本身
# 中文:编码之后UTF-8 下. 一个中文3个字节


# s = "饿了么"
# bs = s.encode("GBK")    # b'\xb6\xf6\xc1\xcb\xc3\xb4' GBK 一个中文:２个字节
# print(bs)

# s = "中"
# print(s.encode("utf-8"))
# print(s.encode("GBK"))

# decode()解码

# bs = b'\xb6\xf6\xc1\xcb\xc3\xb4'    # 从别人那里读到的   GBK
#
# # 编程人认识的东西
# s = bs.decode("GBK")    # 解码之后是字符串, 用什么编码就用什么解码
# print(s)

# GBK => utf-8
bs = b'\xb6\xf6\xc1\xcb\xc3\xb4'
# 先解码成unicode字符串
s = bs.decode("GBK")
# 在把字符串编码成UTF-8
bss = s.encode("UTF-8")
print(bss)

3、作业与练习

'''

s = "k:1|k1:2|k2:3|k3:4"
lst=s.split("|")
dic={}
for i in lst:
    k,v = i.split(":")
    dic[k]=int(v)
print(dic)

# 有如下值li=[11,22,33,44,55,66,77,88,99,90]
# 将所有大于66的值保存至字典的第一个key中，将小于66的所有值保存到第二个key值中
li=[11,22,33,44,55,66,77,88,99,90]
#法一
# dic={"k1":[],"k2":[]}
# for el in li:
#     if el > 66:
#         dic["k1"].append(el)
#     elif el < 66:
#         dic["k2"].append(el)
#     else:
#         pass
# print(dic)
dic={}
for el in li:
    if el > 66:
        dic.setdefault("k1",[]).append(el)
    elif el < 66:
        dic.setdefault("k2",[]).append(el)
print(dic)
'''