Python基础（Day 10）(对象持久化 str-bytes-bytearray转换)

知识点总结：

1. 对象持久化（通过序列化实现）
2. str - bytes - bytearray

---

扁平序列化

生成data.txt文本文件

scores = [99, 88, 77, 5, 4, 3]


def write_scores():
	"""会在当前脚本文件同级目录下生成data.txt文件，并以str形式写入scores"""
    with open('data.txt', 'w', encoding='utf8') as f:
        f.write(str(scores))
        f.flush()
        f.close()


def read_scores():
	"""通过eval()函数将读取的str转为list类型"""
    with open('data.txt', 'r', encoding='utf8') as f:
        lst = eval(f.read())
        print(type(lst))
        print(lst)


if __name__ == '__main__':
    read_scores()

# 输出
<class 'bytes'>
b'\x80\x03]q\x00(KcKXKMK\x05K\x04K\x03e.'

---

通过pickle转为str序列化

import pickle

scores = [99, 88, 77, 5, 4, 3]


def write_scores():
	"""通过pickle直接将对象序列化"""
    with open('data.txt', 'w', encoding='utf8') as f:
        f.write(str(pickle.dumps(scores)))
        f.flush()
        f.close()


def read_scores():
	"""通过pickle直接将对象反序列化"""
    with open('data.txt', 'r', encoding='utf8') as f:
        lst = pickle.loads(eval(f.read()))
        print(type(lst))
        print(lst)


if __name__ == '__main__':
    write_scores()
    read_scores()

# 输出
<class 'list'>
[99, 88, 77, 5, 4, 3]

---

通过pickle直接将对象序列化

生成pickle.db二进制文件

import pickle

scores = [99, 88, 77, 5, 4, 3]


def write_scores():
    pickle.dump(scores, open('pickle.db', 'wb'))


def read_scores():
        lst = pickle.load(open('pickle.db', 'rb'))
        print(type(lst))
        print(lst)


if __name__ == '__main__':
    write_scores()
    read_scores()

---

通过shelve序列化

生成存储文件
shelve.student.bak
shelve.student.dat
shelve.student.dir

import pickle
import shelve


scores = [99, 88, 77, 5, 4, 3]
student = {'name':'Tom','age':20}


def write_scores():
    db = shelve.open('shelve.student')
    db['stu'] = student
    db['scores'] = scores


def read_scores():
    db = shelve.open('shelve.student')
    print(len(db))
    temp_stu = db['stu']
    print(type(temp_stu))
    print(temp_stu)
    temp_scores = db['scores']
    print(type(temp_scores))
    print(temp_scores)

    del db['stu']
    print(db['stu'])


if __name__ == '__main__':
    write_scores()
    read_scores()

# 输出
2
<class 'dict'>
{'name': 'Tom', 'age': 20}
<class 'list'>
[99, 88, 77, 5, 4, 3]
Traceback (most recent call last):
  File "C:\Users\u6072479\AppData\Local\Programs\Python\Python36\lib\shelve.py", line 111, in __getitem__
    value = self.cache[key]
KeyError: 'stu'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:/Users/u6072479/PycharmProjects/numpy-practice/20191127/main.py", line 31, in <module>
    read_scores()
  File "C:/Users/u6072479/PycharmProjects/numpy-practice/20191127/main.py", line 26, in read_scores
    print(db['stu'])
  File "C:\Users\u6072479\AppData\Local\Programs\Python\Python36\lib\shelve.py", line 113, in __getitem__
    f = BytesIO(self.dict[key.encode(self.keyencoding)])
  File "C:\Users\u6072479\AppData\Local\Programs\Python\Python36\lib\dbm\dumb.py", line 148, in __getitem__
    pos, siz = self._index[key]     # may raise KeyError
KeyError: b'stu'

Process finished with exit code 1

---

字符串本质

>>> s1 = 'ABC'
>>> s1.encode('ASCII')
b'ABC'
>>> s2 = 'Python基础'
>>> s2.encode('ASCII')
# ASCII不支持汉字
Traceback (most recent call last):
  File "<input>", line 1, in <module>
UnicodeEncodeError: 'ascii' codec can't encode characters in position 6-7: ordinal not in range(128)
>>>  s2.encode('utf8')
b'Python\xe5\x9f\xba\xe7\xa1\x80'
>>> s3 = '即'
# utf8编码一个汉字
>>> s3.encode('UTF8')
b'\xe5\x8d\xb3'
# utf16编码一个汉字
>>> s3.encode('UTF16')
b'\xff\xfesS'
>>> b1 = b'\xe5\x8d\xb3'
# 解码回str
>>> b1.decode('utf8')
'即'