In [1]:

    

s = 'あいうえお'


    

In [2]:

    

b = s.encode('unicode-escape')


    

In [3]:

    

print(b)


    

    




b'\\u3042\\u3044\\u3046\\u3048\\u304a'

In [4]:

    

print(type(b))


    

    




<class 'bytes'>

In [5]:

    

s_from_b = b.decode('unicode-escape')


    

In [6]:

    

print(s_from_b)


    

    




あいうえお

In [7]:

    

print(type(s_from_b))


    

    




<class 'str'>

In [8]:

    

s_from_b_error = b.decode('utf-8')


    

In [9]:

    

print(s_from_b_error)


    

    




\u3042\u3044\u3046\u3048\u304a

In [10]:

    

print(type(s_from_b_error))


    

    




<class 'str'>

In [11]:

    

s_from_s = s_from_b_error.encode().decode('unicode-escape')


    

In [12]:

    

print(s_from_s)


    

    




あいうえお

In [13]:

    

print(type(s_from_s))


    

    




<class 'str'>

In [14]:

    

import codecs

s_from_s_codecs = codecs.decode(s_from_b_error, 'unicode-escape')


    

In [15]:

    

print(s_from_s_codecs)


    

    




あいうえお

In [16]:

    

print(type(s_from_s_codecs))


    

    




<class 'str'>

In [17]:

    

s_ascii = ascii('あ')


    

In [18]:

    

print(s_ascii)


    

    




'\u3042'

In [19]:

    

print(type(s_ascii))


    

    




<class 'str'>

In [20]:

    

print(s_ascii[0])


    

    




'

In [21]:

    

print(s_ascii[-1])


    

    




'

In [22]:

    

print(len(s_ascii))


    

    




8

In [23]:

    

print(ascii('あ') == "'\\u3042'")


    

    




True

In [24]:

    

s_unicode_escape = ascii('あ')[1:-1]


    

In [25]:

    

print(s_unicode_escape)


    

    




\u3042

In [26]:

    

print(type(s_unicode_escape))


    

    




<class 'str'>

In [27]:

    

print(s_unicode_escape == '\\u3042')


    

    




True

In [28]:

    

print('\u3042')


    

    




あ

In [29]:

    

print(len('\u3042'))


    

    




1

In [30]:

    

print('\u3042' == 'あ')


    

    




True

In [31]:

    

print('\\u3042')


    

    




\u3042

In [32]:

    

print(r'\u3042')


    

    




\u3042

In [33]:

    

print(len(r'\u3042'))


    

    




6

In [34]:

    

with open('data/src/unicode_escape.txt') as f:
    s = f.read()
    print(s)
    print(type(s))
    print(len(s))


    

    




\u3042\u3044\u3046\u3048\u304a
<class 'str'>
30

In [35]:

    

with open('data/src/unicode_escape.txt', encoding='unicode-escape') as f:
    s = f.read()
    print(s)
    print(type(s))
    print(len(s))


    

    




あいうえお
<class 'str'>
5

In [36]:

    

b_json = b'{"a": "\u3042"}'


    

In [37]:

    

print(b_json)


    

    




b'{"a": "\\u3042"}'

In [38]:

    

print(b_json.decode())


    

    




{"a": "\u3042"}

In [39]:

    

print(b_json.decode('unicode-escape'))


    

    




{"a": "あ"}

In [40]:

    

import json


    

In [41]:

    

print(json.loads(b_json.decode()))


    

    




{'a': 'あ'}

In [42]:

    

print(type(json.loads(b_json.decode())))


    

    




<class 'dict'>

In [43]:

    

print(json.loads(b_json))


    

    




{'a': 'あ'}