[技术交流] str与bytes

# 创建三个类型的字符串,并且打印
a1 = "马强"
a2 = "maqiang"
a3 = "123@#"
print(type(a1), a1)
print(type(a2), a2)
print(type(a3), a3)
"""
输出 
<class 'str'> 马强
<class 'str'> maqiang
<class 'str'> 123@#
"""

# 将其转变为字节串
b1 = a1.encode()    # bytes(a1,"utf-8")
b2 = a2.encode()    # bytes(a2,"utf-8")
b3 = a3.encode("gbk")    # bytes(a3,"utf-8")
# 用bytes转换encoding不能省
print(type(b1), b1)
print(type(b2), b2)
print(type(b3), b3)
"""
输出
<class 'bytes'> b'\xe9\xa9\xac\xe5\xbc\xba' 
<class 'bytes'> b'maqiang'
<class 'bytes'> b'123@#'
"""
# 将其转变回字符串
c1 = str(b1, "utf-8")  # b1.decode("utf-8") , encoding 一定要加 且与编码时相同
c2 = str(b2, "utf-8")  # b2.decode("utf-8")
c3 = str(b3, "utf-8")  # b3.decode("utf-8") encoding 一定要加 且可以与编码时不相同

print("c1", type(c1), c1)
print("c2", type(c2), c2)
print("c3", type(c3), c3)
"""
输出1 - 加都加encoding
c1 <class 'str'> 马强
c2 <class 'str'> maqiang
c3 <class 'str'> 123@#
输出2 - 都不加 encoding
c1 <class 'str'> b'\xe9\xa9\xac\xe5\xbc\xba'
c2 <class 'str'> b'maqiang'
c3 <class 'str'> b'123@#'
"""

print(a1+a2)  # 同str
print(a1+b2)  # 不同
print(b1+b2)  # 同bytes
print(b1+b3)  # 不同编码

"""
输出
马强maqiang
报错 can only concatenate str (not "bytes") to str
b'\xe9\xa9\xac\xe5\xbc\xbamaqiang'
b'\xe9\xa9\xac\xe5\xbc\xba123@#'
"""