如何使一个Python类序列化?

class FileItem:
    def __init__(self, fname):
        self.fname = fname

尝试序列化为JSON:

>>> import json
>>> x = FileItem('/foo/bar')
>>> json.dumps(x)
TypeError: Object of type 'FileItem' is not JSON serializable

当前回答

我喜欢Onur的答案,但会扩展到包括一个可选的toJSON()方法,用于对象序列化自己:

def dumper(obj):
    try:
        return obj.toJSON()
    except:
        return obj.__dict__
print json.dumps(some_big_object, default=dumper, indent=2)

其他回答

你知道预期产量是多少吗?例如,这个可以吗?

>>> f  = FileItem("/foo/bar")
>>> magic(f)
'{"fname": "/foo/bar"}'

在这种情况下,你只需调用json.dumps(f.__dict__)。

如果您想要更多自定义输出,那么您必须继承JSONEncoder并实现您自己的自定义序列化。

对于一个简单的例子,请参见下面。

>>> from json import JSONEncoder
>>> class MyEncoder(JSONEncoder):
        def default(self, o):
            return o.__dict__    

>>> MyEncoder().encode(f)
'{"fname": "/foo/bar"}'

然后你把这个类作为cls kwarg传递给json.dumps()方法:

json.dumps(cls=MyEncoder)

如果还想解码,则必须向JSONDecoder类提供一个自定义object_hook。例如:

>>> def from_json(json_object):
        if 'fname' in json_object:
            return FileItem(json_object['fname'])
>>> f = JSONDecoder(object_hook = from_json).decode('{"fname": "/foo/bar"}')
>>> f
<__main__.FileItem object at 0x9337fac>
>>> 
import simplejson

class User(object):
    def __init__(self, name, mail):
        self.name = name
        self.mail = mail

    def _asdict(self):
        return self.__dict__

print(simplejson.dumps(User('alice', 'alice@mail.com')))

如果使用标准json,则需要定义一个默认函数

import json
def default(o):
    return o._asdict()

print(json.dumps(User('alice', 'alice@mail.com'), default=default))

为了在10年前的火灾中再添加一个日志,我还将为这个任务提供数据类向导,假设您使用的是Python 3.6+。这可以很好地用于数据类,这实际上是3.7+版本的python内置模块。

dataclass-wizard库将把对象(及其所有属性递归地)转换为dict,并使用fromdict使反向(反序列化)非常简单。另外,这里是PyPi链接:https://pypi.org/project/dataclass-wizard/。

import dataclass_wizard
import dataclasses

@dataclasses.dataclass
class A:
    hello: str
    a_field: int

obj = A('world', 123)
a_dict = dataclass_wizard.asdict(obj)
# {'hello': 'world', 'aField': 123}

或者如果你想要一个字符串:

a_str = jsons.dumps(dataclass_wizard.asdict(obj))

或者您的类是否从dataclass_wizard扩展。JSONWizard:

a_str = your_object.to_json()

最后,标准库还支持Union类型的数据类,这基本上意味着可以将dict反序列化为类C1或C2的对象。例如:

from dataclasses import dataclass

from dataclass_wizard import JSONWizard

@dataclass
class Outer(JSONWizard):

    class _(JSONWizard.Meta):
        tag_key = 'tag'
        auto_assign_tags = True

    my_string: str
    inner: 'A | B'  # alternate syntax: `inner: typing.Union['A', 'B']`

@dataclass
class A:
    my_field: int

@dataclass
class B:
    my_field: str


my_dict = {'myString': 'test', 'inner': {'tag': 'B', 'myField': 'test'}}
obj = Outer.from_dict(my_dict)

# True
assert repr(obj) == "Outer(my_string='test', inner=B(my_field='test'))"

obj.to_json()
# {"myString": "test", "inner": {"myField": "test", "tag": "B"}}

我们经常在日志文件中转储JSON格式的复杂字典。虽然大多数字段携带重要信息,但我们不太关心内置的类对象(例如子进程)。Popen对象)。由于存在这些不可序列化的对象,对json.dumps()的调用会失败。

为了解决这个问题,我构建了一个小函数来转储对象的字符串表示形式,而不是转储对象本身。如果您正在处理的数据结构嵌套太多,您可以指定嵌套的最大级别/深度。

from time import time

def safe_serialize(obj , max_depth = 2):

    max_level = max_depth

    def _safe_serialize(obj , current_level = 0):

        nonlocal max_level

        # If it is a list
        if isinstance(obj , list):

            if current_level >= max_level:
                return "[...]"

            result = list()
            for element in obj:
                result.append(_safe_serialize(element , current_level + 1))
            return result

        # If it is a dict
        elif isinstance(obj , dict):

            if current_level >= max_level:
                return "{...}"

            result = dict()
            for key , value in obj.items():
                result[f"{_safe_serialize(key , current_level + 1)}"] = _safe_serialize(value , current_level + 1)
            return result

        # If it is an object of builtin class
        elif hasattr(obj , "__dict__"):
            if hasattr(obj , "__repr__"):
                result = f"{obj.__repr__()}_{int(time())}"
            else:
                try:
                    result = f"{obj.__class__.__name__}_object_{int(time())}"
                except:
                    result = f"object_{int(time())}"
            return result

        # If it is anything else
        else:
            return obj

    return _safe_serialize(obj)

由于字典也可以有不可序列化的键,转储它们的类名或对象表示将导致所有键都具有相同的名称,这将抛出错误,因为所有键都需要有唯一的名称,这就是为什么当前时间Since epoch被int(time())附加到对象名称。

可以使用以下具有不同级别/深度的嵌套字典来测试该函数

d = {
    "a" : {
        "a1" : {
            "a11" : {
                "a111" : "some_value" ,
                "a112" : "some_value" ,
            } ,
            "a12" : {
                "a121" : "some_value" ,
                "a122" : "some_value" ,
            } ,
        } ,
        "a2" : {
            "a21" : {
                "a211" : "some_value" ,
                "a212" : "some_value" ,
            } ,
            "a22" : {
                "a221" : "some_value" ,
                "a222" : "some_value" ,
            } ,
        } ,
    } ,
    "b" : {
        "b1" : {
            "b11" : {
                "b111" : "some_value" ,
                "b112" : "some_value" ,
            } ,
            "b12" : {
                "b121" : "some_value" ,
                "b122" : "some_value" ,
            } ,
        } ,
        "b2" : {
            "b21" : {
                "b211" : "some_value" ,
                "b212" : "some_value" ,
            } ,
            "b22" : {
                "b221" : "some_value" ,
                "b222" : "some_value" ,
            } ,
        } ,
    } ,
    "c" : subprocess.Popen("ls -l".split() , stdout = subprocess.PIPE , stderr = subprocess.PIPE) ,
}

执行以下命令将会得到-

print("LEVEL 3")
print(json.dumps(safe_serialize(d , 3) , indent = 4))

print("\n\n\nLEVEL 2")
print(json.dumps(safe_serialize(d , 2) , indent = 4))

print("\n\n\nLEVEL 1")
print(json.dumps(safe_serialize(d , 1) , indent = 4))

结果:

LEVEL 3
{
    "a": {
        "a1": {
            "a11": "{...}",
            "a12": "{...}"
        },
        "a2": {
            "a21": "{...}",
            "a22": "{...}"
        }
    },
    "b": {
        "b1": {
            "b11": "{...}",
            "b12": "{...}"
        },
        "b2": {
            "b21": "{...}",
            "b22": "{...}"
        }
    },
    "c": "<Popen: returncode: None args: ['ls', '-l']>"
}



LEVEL 2
{
    "a": {
        "a1": "{...}",
        "a2": "{...}"
    },
    "b": {
        "b1": "{...}",
        "b2": "{...}"
    },
    "c": "<Popen: returncode: None args: ['ls', '-l']>"
}



LEVEL 1
{
    "a": "{...}",
    "b": "{...}",
    "c": "<Popen: returncode: None args: ['ls', '-l']>"
}

[注意]:仅在不关心内置类对象的序列化时使用此选项。

基于Quinten Cabo的回答:

def sterilize(obj):
    """Make an object more ameniable to dumping as json
    """
    if type(obj) in (str, float, int, bool, type(None)):
        return obj
    elif isinstance(obj, dict):
        return {k: sterilize(v) for k, v in obj.items()}
    list_ret = []
    dict_ret = {}
    for a in dir(obj):
        if a == '__iter__' and callable(obj.__iter__):
            list_ret.extend([sterilize(v) for v in obj])
        elif a == '__dict__':
            dict_ret.update({k: sterilize(v) for k, v in obj.__dict__.items() if k not in ['__module__', '__dict__', '__weakref__', '__doc__']})
        elif a not in ['__doc__', '__module__']:
            aval = getattr(obj, a)
            if type(aval) in (str, float, int, bool, type(None)):
                dict_ret[a] = aval
            elif a != '__class__' and a != '__objclass__' and isinstance(aval, type):
                dict_ret[a] = sterilize(aval)
    if len(list_ret) == 0:
        if len(dict_ret) == 0:
            return repr(obj)
        return dict_ret
    else:
        if len(dict_ret) == 0:
            return list_ret
    return (list_ret, dict_ret)

区别在于

Works for any iterable instead of just list and tuple (it works for NumPy arrays, etc.) Works for dynamic types (ones that contain a __dict__). Includes native types float and None so they don't get converted to string. Classes that have __dict__ and members will mostly work (if the __dict__ and member names collide, you will only get one - likely the member) Classes that are lists and have members will look like a tuple of the list and a dictionary Python3 (that isinstance() call may be the only thing that needs changing)