一个非常简单的一行程序解决方案

import json

json.dumps(your_object, default=lambda __o: __o.__dict__)

结束!

下面是一个测试。

import json
from dataclasses import dataclass


@dataclass
class Company:
    id: int
    name: str

@dataclass
class User:
    id: int
    name: str
    email: str
    company: Company


company = Company(id=1, name="Example Ltd")
user = User(id=1, name="John Doe", email="john@doe.net", company=company)


json.dumps(user, default=lambda __o: __o.__dict__)

输出:

{
  "id": 1, 
  "name": "John Doe", 
  "email": "john@doe.net", 
  "company": {
    "id": 1, 
    "name": "Example Ltd"
  }
}

import json

class Foo(object):
    def __init__(self):
        self.bar = 'baz'
        self._qux = 'flub'

    def somemethod(self):
        pass

def default(instance):
    return {k: v
            for k, v in vars(instance).items()
            if not str(k).startswith('_')}

json_foo = json.dumps(Foo(), default=default)
assert '{"bar": "baz"}' == json_foo

print(json_foo)

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)

只需要像这样添加to_json方法到你的类中:

def to_json(self):
  return self.message # or how you want it to be serialized

然后将这段代码(来自这个答案)添加到所有内容的顶部:

from json import JSONEncoder

def _default(self, obj):
    return getattr(obj.__class__, "to_json", _default.default)(obj)

_default.default = JSONEncoder().default
JSONEncoder.default = _default

这将会在导入json模块时monkey-patch，所以 JSONEncoder.default()自动检查特殊的to_json() 方法，并使用它对找到的对象进行编码。

就像Onur说的，但是这次你不需要更新项目中的每个json.dumps()。

如果你能够安装一个软件包，我建议你试试dill，它在我的项目中工作得很好。这个包的一个优点是它具有与pickle相同的接口，因此如果您已经在项目中使用了pickle，则可以简单地替换为dill并查看脚本是否运行，而无需更改任何代码。所以这是一个非常便宜的解决方案!

(完全反披露:我与莳萝项目没有任何关联，也从未参与过。)

安装包:

pip install dill

然后编辑你的代码导入莳萝而不是pickle:

# import pickle
import dill as pickle

运行脚本，看看它是否有效。(如果是的话，你可能想要清理你的代码，这样你就不再隐藏pickle模块的名字了!)

关于dill可以和不能序列化的数据类型的一些细节，来自项目页面:

dill can pickle the following standard types: none, type, bool, int, long, float, complex, str, unicode, tuple, list, dict, file, buffer, builtin, both old and new style classes, instances of old and new style classes, set, frozenset, array, functions, exceptions dill can also pickle more ‘exotic’ standard types: functions with yields, nested functions, lambdas, cell, method, unboundmethod, module, code, methodwrapper, dictproxy, methoddescriptor, getsetdescriptor, memberdescriptor, wrapperdescriptor, xrange, slice, notimplemented, ellipsis, quit dill cannot yet pickle these standard types: frame, generator, traceback