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。

class DObject(json.JSONEncoder):
    def delete_not_related_keys(self, _dict):
        for key in ["skipkeys", "ensure_ascii", "check_circular", "allow_nan", "sort_keys", "indent"]:
            try:
                del _dict[key]
            except:
                continue

    def default(self, o):
        if hasattr(o, '__dict__'):
            my_dict = o.__dict__.copy()
            self.delete_not_related_keys(my_dict)
            return my_dict
        else:
            return o

a = DObject()
a.name = 'abdul wahid'
b = DObject()
b.name = a

print(json.dumps(b, cls=DObject))

这是我的3美分… 这演示了一个树状python对象的显式json序列化。 注意:如果你真的想要这样的代码，你可以使用twisted FilePath类。

import json, sys, os

class File:
    def __init__(self, path):
        self.path = path

    def isdir(self):
        return os.path.isdir(self.path)

    def isfile(self):
        return os.path.isfile(self.path)

    def children(self):        
        return [File(os.path.join(self.path, f)) 
                for f in os.listdir(self.path)]

    def getsize(self):        
        return os.path.getsize(self.path)

    def getModificationTime(self):
        return os.path.getmtime(self.path)

def _default(o):
    d = {}
    d['path'] = o.path
    d['isFile'] = o.isfile()
    d['isDir'] = o.isdir()
    d['mtime'] = int(o.getModificationTime())
    d['size'] = o.getsize() if o.isfile() else 0
    if o.isdir(): d['children'] = o.children()
    return d

folder = os.path.abspath('.')
json.dump(File(folder), sys.stdout, default=_default)

我最喜欢Lost Koder的方法。当我试图序列化成员/方法不可序列化的更复杂的对象时，我遇到了问题。这是我的实现，工作在更多的对象:

class Serializer(object):
    @staticmethod
    def serialize(obj):
        def check(o):
            for k, v in o.__dict__.items():
                try:
                    _ = json.dumps(v)
                    o.__dict__[k] = v
                except TypeError:
                    o.__dict__[k] = str(v)
            return o
        return json.dumps(check(obj).__dict__, indent=2)

解决这个问题有很多方法。'ObjDict' (pip install object)是另一个。重点是提供像javascript一样的对象，它也可以像字典一样最好地处理从JSON加载的数据，但还有其他功能也很有用。这为原始问题提供了另一种解决方案。

前几天我遇到了这个问题，并为Python对象实现了一个更通用的Encoder版本，可以处理嵌套对象和继承字段:

import json
import inspect

class ObjectEncoder(json.JSONEncoder):
    def default(self, obj):
        if hasattr(obj, "to_json"):
            return self.default(obj.to_json())
        elif hasattr(obj, "__dict__"):
            d = dict(
                (key, value)
                for key, value in inspect.getmembers(obj)
                if not key.startswith("__")
                and not inspect.isabstract(value)
                and not inspect.isbuiltin(value)
                and not inspect.isfunction(value)
                and not inspect.isgenerator(value)
                and not inspect.isgeneratorfunction(value)
                and not inspect.ismethod(value)
                and not inspect.ismethoddescriptor(value)
                and not inspect.isroutine(value)
            )
            return self.default(d)
        return obj

例子:

class C(object):
    c = "NO"
    def to_json(self):
        return {"c": "YES"}

class B(object):
    b = "B"
    i = "I"
    def __init__(self, y):
        self.y = y
        
    def f(self):
        print "f"

class A(B):
    a = "A"
    def __init__(self):
        self.b = [{"ab": B("y")}]
        self.c = C()

print json.dumps(A(), cls=ObjectEncoder, indent=2, sort_keys=True)

结果:

{
  "a": "A", 
  "b": [
    {
      "ab": {
        "b": "B", 
        "i": "I", 
        "y": "y"
      }
    }
  ], 
  "c": {
    "c": "YES"
  }, 
  "i": "I"
}