我想将JSON数据转换为Python对象。
我从Facebook API收到JSON数据对象，我想将其存储在数据库中。
我的当前视图在Django (Python)(请求。POST包含JSON):
response = request.POST
user = FbApiUser(user_id = response['id'])
user.name = response['name']
user.username = response['username']
user.save()
这很好，但是如何处理复杂的JSON数据对象呢? 如果我能以某种方式将这个JSON对象转换为易于使用的Python对象，是不是会更好?
对于复杂的对象，可以使用JSON Pickle
Python库，用于将任意对象图序列化为JSON。 它几乎可以接受任何Python对象并将对象转换为JSON。 此外，它还可以将对象重新构造回Python。
查看JSON模块文档中的专门化JSON对象解码一节。您可以使用它将JSON对象解码为特定的Python类型。
这里有一个例子:
class User(object):
def __init__(self, name, username):
self.name = name
self.username = username
import json
def object_decoder(obj):
if '__type__' in obj and obj['__type__'] == 'User':
return User(obj['name'], obj['username'])
return obj
json.loads('{"__type__": "User", "name": "John Smith", "username": "jsmith"}',
object_hook=object_decoder)
print type(User) # -> <type 'type'>
更新
如果你想通过json模块访问字典中的数据，可以这样做:
user = json.loads('{"__type__": "User", "name": "John Smith", "username": "jsmith"}')
print user['name']
print user['username']
就像一本普通的字典。
我已经编写了一个名为any2any的小型(反)序列化框架，它可以帮助在两种Python类型之间进行复杂的转换。
在您的情况下，我猜您想从字典(通过json.loads获得)转换为复杂的对象response.education;Response.name，具有嵌套结构response.education.id，等等… 这就是这个框架的用途。文档还不是很好，但是通过使用any2any.simple。MappingToObject，你应该可以很容易地做到。如果需要帮助，请询问。
更新
在Python3中，你可以使用SimpleNamespace和object_hook在一行中完成:
import json
from types import SimpleNamespace
data = '{"name": "John Smith", "hometown": {"name": "New York", "id": 123}}'
# Parse JSON into an object with attributes corresponding to dict keys.
x = json.loads(data, object_hook=lambda d: SimpleNamespace(**d))
print(x.name, x.hometown.name, x.hometown.id)
旧答案(Python2)
在Python2中，你可以使用namedtuple和object_hook在一行中完成(但对于嵌套对象非常慢):
import json
from collections import namedtuple
data = '{"name": "John Smith", "hometown": {"name": "New York", "id": 123}}'
# Parse JSON into an object with attributes corresponding to dict keys.
x = json.loads(data, object_hook=lambda d: namedtuple('X', d.keys())(*d.values()))
print x.name, x.hometown.name, x.hometown.id
或者，为了便于重用:
def _json_object_hook(d): return namedtuple('X', d.keys())(*d.values())
def json2obj(data): return json.loads(data, object_hook=_json_object_hook)
x = json2obj(data)
如果希望它处理不是很好的属性名称的键，请检查namedtuple的rename参数。
你可以试试这个:
class User(object):
def __init__(self, name, username):
self.name = name
self.username = username
import json
j = json.loads(your_json)
u = User(**j)
只需创建一个新对象，并将参数作为映射传递。
你也可以有一个带有对象的JSON:
import json
class Address(object):
def __init__(self, street, number):
self.street = street
self.number = number
def __str__(self):
return "{0} {1}".format(self.street, self.number)
class User(object):
def __init__(self, name, address):
self.name = name
self.address = Address(**address)
def __str__(self):
return "{0} ,{1}".format(self.name, self.address)
if __name__ == '__main__':
js = '''{"name":"Cristian", "address":{"street":"Sesame","number":122}}'''
j = json.loads(js)
print(j)
u = User(**j)
print(u)
这里有一个快速而肮脏的json pickle替代方案
import json
class User:
def __init__(self, name, username):
self.name = name
self.username = username
def to_json(self):
return json.dumps(self.__dict__)
@classmethod
def from_json(cls, json_str):
json_dict = json.loads(json_str)
return cls(**json_dict)
# example usage
User("tbrown", "Tom Brown").to_json()
User.from_json(User("tbrown", "Tom Brown").to_json()).to_json()
这不是代码高尔夫，但这里是我使用类型的最短技巧。SimpleNamespace作为JSON对象的容器。
与namedtuple解决方案相比，它是:
可能更快/更小，因为它没有为每个对象创建一个类 更短的 没有重命名选项，对于不是有效标识符的键可能有相同的限制(在幕后使用setattr)
例子:
from __future__ import print_function
import json
try:
from types import SimpleNamespace as Namespace
except ImportError:
# Python 2.x fallback
from argparse import Namespace
data = '{"name": "John Smith", "hometown": {"name": "New York", "id": 123}}'
x = json.loads(data, object_hook=lambda d: Namespace(**d))
print (x.name, x.hometown.name, x.hometown.id)
修改@DS响应位，从一个文件加载:
def _json_object_hook(d): return namedtuple('X', d.keys())(*d.values())
def load_data(file_name):
with open(file_name, 'r') as file_data:
return file_data.read().replace('\n', '')
def json2obj(file_name): return json.loads(load_data(file_name), object_hook=_json_object_hook)
有一点:它不能加载前面有数字的项目。是这样的:
{
"1_first_item": {
"A": "1",
"B": "2"
}
}
因为“1_first_item”不是一个有效的python字段名。
Python3.x
以我的知识，我能找到的最好的方法是。 注意，这段代码也处理set()。 这种方法是通用的，只需要类的扩展(在第二个例子中)。 请注意，我只是对文件执行此操作，但是很容易根据自己的喜好修改行为。
然而，这是一个编解码器。
再做一点工作，就可以用其他方式构造类。 我假设有一个默认构造函数来实例它，然后更新类dict。
import json
import collections
class JsonClassSerializable(json.JSONEncoder):
REGISTERED_CLASS = {}
def register(ctype):
JsonClassSerializable.REGISTERED_CLASS[ctype.__name__] = ctype
def default(self, obj):
if isinstance(obj, collections.Set):
return dict(_set_object=list(obj))
if isinstance(obj, JsonClassSerializable):
jclass = {}
jclass["name"] = type(obj).__name__
jclass["dict"] = obj.__dict__
return dict(_class_object=jclass)
else:
return json.JSONEncoder.default(self, obj)
def json_to_class(self, dct):
if '_set_object' in dct:
return set(dct['_set_object'])
elif '_class_object' in dct:
cclass = dct['_class_object']
cclass_name = cclass["name"]
if cclass_name not in self.REGISTERED_CLASS:
raise RuntimeError(
"Class {} not registered in JSON Parser"
.format(cclass["name"])
)
instance = self.REGISTERED_CLASS[cclass_name]()
instance.__dict__ = cclass["dict"]
return instance
return dct
def encode_(self, file):
with open(file, 'w') as outfile:
json.dump(
self.__dict__, outfile,
cls=JsonClassSerializable,
indent=4,
sort_keys=True
)
def decode_(self, file):
try:
with open(file, 'r') as infile:
self.__dict__ = json.load(
infile,
object_hook=self.json_to_class
)
except FileNotFoundError:
print("Persistence load failed "
"'{}' do not exists".format(file)
)
class C(JsonClassSerializable):
def __init__(self):
self.mill = "s"
JsonClassSerializable.register(C)
class B(JsonClassSerializable):
def __init__(self):
self.a = 1230
self.c = C()
JsonClassSerializable.register(B)
class A(JsonClassSerializable):
def __init__(self):
self.a = 1
self.b = {1, 2}
self.c = B()
JsonClassSerializable.register(A)
A().encode_("test")
b = A()
b.decode_("test")
print(b.a)
print(b.b)
print(b.c.a)
Edit
通过更多的研究，我发现了一种不需要SUPERCLASS寄存器方法调用的泛化方法，使用元类
import json
import collections
REGISTERED_CLASS = {}
class MetaSerializable(type):
def __call__(cls, *args, **kwargs):
if cls.__name__ not in REGISTERED_CLASS:
REGISTERED_CLASS[cls.__name__] = cls
return super(MetaSerializable, cls).__call__(*args, **kwargs)
class JsonClassSerializable(json.JSONEncoder, metaclass=MetaSerializable):
def default(self, obj):
if isinstance(obj, collections.Set):
return dict(_set_object=list(obj))
if isinstance(obj, JsonClassSerializable):
jclass = {}
jclass["name"] = type(obj).__name__
jclass["dict"] = obj.__dict__
return dict(_class_object=jclass)
else:
return json.JSONEncoder.default(self, obj)
def json_to_class(self, dct):
if '_set_object' in dct:
return set(dct['_set_object'])
elif '_class_object' in dct:
cclass = dct['_class_object']
cclass_name = cclass["name"]
if cclass_name not in REGISTERED_CLASS:
raise RuntimeError(
"Class {} not registered in JSON Parser"
.format(cclass["name"])
)
instance = REGISTERED_CLASS[cclass_name]()
instance.__dict__ = cclass["dict"]
return instance
return dct
def encode_(self, file):
with open(file, 'w') as outfile:
json.dump(
self.__dict__, outfile,
cls=JsonClassSerializable,
indent=4,
sort_keys=True
)
def decode_(self, file):
try:
with open(file, 'r') as infile:
self.__dict__ = json.load(
infile,
object_hook=self.json_to_class
)
except FileNotFoundError:
print("Persistence load failed "
"'{}' do not exists".format(file)
)
class C(JsonClassSerializable):
def __init__(self):
self.mill = "s"
class B(JsonClassSerializable):
def __init__(self):
self.a = 1230
self.c = C()
class A(JsonClassSerializable):
def __init__(self):
self.a = 1
self.b = {1, 2}
self.c = B()
A().encode_("test")
b = A()
b.decode_("test")
print(b.a)
# 1
print(b.b)
# {1, 2}
print(b.c.a)
# 1230
print(b.c.c.mill)
# s
在寻找解决方案时，我偶然发现了这个博客:https://blog.mosthege.net/2016/11/12/json-deserialization-of-nested-objects/
它使用与前面回答中相同的技术，但使用了装饰器。 我发现另一件有用的事情是，它在反序列化结束时返回一个类型化对象
class JsonConvert(object):
class_mappings = {}
@classmethod
def class_mapper(cls, d):
for keys, cls in clsself.mappings.items():
if keys.issuperset(d.keys()): # are all required arguments present?
return cls(**d)
else:
# Raise exception instead of silently returning None
raise ValueError('Unable to find a matching class for object: {!s}'.format(d))
@classmethod
def complex_handler(cls, Obj):
if hasattr(Obj, '__dict__'):
return Obj.__dict__
else:
raise TypeError('Object of type %s with value of %s is not JSON serializable' % (type(Obj), repr(Obj)))
@classmethod
def register(cls, claz):
clsself.mappings[frozenset(tuple([attr for attr,val in cls().__dict__.items()]))] = cls
return cls
@classmethod
def to_json(cls, obj):
return json.dumps(obj.__dict__, default=cls.complex_handler, indent=4)
@classmethod
def from_json(cls, json_str):
return json.loads(json_str, object_hook=cls.class_mapper)
用法:
@JsonConvert.register
class Employee(object):
def __init__(self, Name:int=None, Age:int=None):
self.Name = Name
self.Age = Age
return
@JsonConvert.register
class Company(object):
def __init__(self, Name:str="", Employees:[Employee]=None):
self.Name = Name
self.Employees = [] if Employees is None else Employees
return
company = Company("Contonso")
company.Employees.append(Employee("Werner", 38))
company.Employees.append(Employee("Mary"))
as_json = JsonConvert.to_json(company)
from_json = JsonConvert.from_json(as_json)
as_json_from_json = JsonConvert.to_json(from_json)
assert(as_json_from_json == as_json)
print(as_json_from_json)
如果你使用的是Python 3.5+，你可以使用json来序列化和反序列化到普通的旧Python对象:
import jsons
response = request.POST
# You'll need your class attributes to match your dict keys, so in your case do:
response['id'] = response.pop('user_id')
# Then you can load that dict into your class:
user = jsons.load(response, FbApiUser)
user.save()
你也可以让FbApiUser从jsons继承。JsonSerializable更优雅:
user = FbApiUser.from_json(response)
如果你的类由Python默认类型组成，比如字符串、整数、列表、日期时间等，这些例子就可以工作。不过，jsons lib需要自定义类型的类型提示。
扩展一下DS的答案，如果你需要对象是可变的(而namedtuple不是)，你可以使用记录类库而不是namedtuple:
import json
from recordclass import recordclass
data = '{"name": "John Smith", "hometown": {"name": "New York", "id": 123}}'
# Parse into a mutable object
x = json.loads(data, object_hook=lambda d: recordclass('X', d.keys())(*d.values()))
修改后的对象可以使用simplejson很容易地转换回json:
x.name = "John Doe"
new_json = simplejson.dumps(x)
既然没有人给出了和我一样的答案，我就把它贴在这里。
这是一个健壮的类，可以轻松地在JSON str和dict之间来回转换，我已经从我的答案复制到另一个问题:
import json
class PyJSON(object):
def __init__(self, d):
if type(d) is str:
d = json.loads(d)
self.from_dict(d)
def from_dict(self, d):
self.__dict__ = {}
for key, value in d.items():
if type(value) is dict:
value = PyJSON(value)
self.__dict__[key] = value
def to_dict(self):
d = {}
for key, value in self.__dict__.items():
if type(value) is PyJSON:
value = value.to_dict()
d[key] = value
return d
def __repr__(self):
return str(self.to_dict())
def __setitem__(self, key, value):
self.__dict__[key] = value
def __getitem__(self, key):
return self.__dict__[key]
json_str = """... JSON string ..."""
py_json = PyJSON(json_str)
如果你正在使用python 3.6+，你可以使用棉花糖-数据类。与上面列出的所有解决方案相反，它既简单，又类型安全:
from marshmallow_dataclass import dataclass
@dataclass
class User:
name: str
user = User.Schema().load({"name": "Ramirez"})
改进lovasoa非常好的答案。
如果你正在使用python 3.6+，你可以使用: PIP安装棉花糖-enum和 PIP安装棉花糖数据类
它简单且类型安全。
你可以在string-json中转换你的类，反之亦然:
从对象到字符串Json:
from marshmallow_dataclass import dataclass
user = User("Danilo","50","RedBull",15,OrderStatus.CREATED)
user_json = User.Schema().dumps(user)
user_json_str = user_json.data
从String Json到Object:
json_str = '{"name":"Danilo", "orderId":"50", "productName":"RedBull", "quantity":15, "status":"Created"}'
user, err = User.Schema().loads(json_str)
print(user,flush=True)
类定义:
class OrderStatus(Enum):
CREATED = 'Created'
PENDING = 'Pending'
CONFIRMED = 'Confirmed'
FAILED = 'Failed'
@dataclass
class User:
def __init__(self, name, orderId, productName, quantity, status):
self.name = name
self.orderId = orderId
self.productName = productName
self.quantity = quantity
self.status = status
name: str
orderId: str
productName: str
quantity: int
status: OrderStatus
如果你使用的是Python 3.6或更新版本，你可以看看squema——一个用于静态类型数据结构的轻量级模块。它使您的代码易于阅读，同时提供简单的数据验证，转换和序列化，而无需额外的工作。你可以把它看作是命名元组和数据类的一种更复杂、更有见解的选择。下面是你如何使用它:
from uuid import UUID
from squema import Squema
class FbApiUser(Squema):
id: UUID
age: int
name: str
def save(self):
pass
user = FbApiUser(**json.loads(response))
user.save()
你可以使用
x = Map(json.loads(response))
x.__class__ = MyClass
在哪里
class Map(dict):
def __init__(self, *args, **kwargs):
super(Map, self).__init__(*args, **kwargs)
for arg in args:
if isinstance(arg, dict):
for k, v in arg.iteritems():
self[k] = v
if isinstance(v, dict):
self[k] = Map(v)
if kwargs:
# for python 3 use kwargs.items()
for k, v in kwargs.iteritems():
self[k] = v
if isinstance(v, dict):
self[k] = Map(v)
def __getattr__(self, attr):
return self.get(attr)
def __setattr__(self, key, value):
self.__setitem__(key, value)
def __setitem__(self, key, value):
super(Map, self).__setitem__(key, value)
self.__dict__.update({key: value})
def __delattr__(self, item):
self.__delitem__(item)
def __delitem__(self, key):
super(Map, self).__delitem__(key)
del self.__dict__[key]
对于通用的、经得起未来考验的解决方案。
我正在寻找一个与recordclass一起工作的解决方案。RecordClass，支持嵌套对象，可用于json序列化和json反序列化。
扩展DS的答案，扩展BeneStr的解决方案，我想出了以下似乎有效的方法:
代码:
import json
import recordclass
class NestedRec(recordclass.RecordClass):
a : int = 0
b : int = 0
class ExampleRec(recordclass.RecordClass):
x : int = None
y : int = None
nested : NestedRec = NestedRec()
class JsonSerializer:
@staticmethod
def dumps(obj, ensure_ascii=True, indent=None, sort_keys=False):
return json.dumps(obj, default=JsonSerializer.__obj_to_dict, ensure_ascii=ensure_ascii, indent=indent, sort_keys=sort_keys)
@staticmethod
def loads(s, klass):
return JsonSerializer.__dict_to_obj(klass, json.loads(s))
@staticmethod
def __obj_to_dict(obj):
if hasattr(obj, "_asdict"):
return obj._asdict()
else:
return json.JSONEncoder().default(obj)
@staticmethod
def __dict_to_obj(klass, s_dict):
kwargs = {
key : JsonSerializer.__dict_to_obj(cls, s_dict[key]) if hasattr(cls,'_asdict') else s_dict[key] \
for key,cls in klass.__annotations__.items() \
if s_dict is not None and key in s_dict
}
return klass(**kwargs)
用法:
example_0 = ExampleRec(x = 10, y = 20, nested = NestedRec( a = 30, b = 40 ) )
#Serialize to JSON
json_str = JsonSerializer.dumps(example_0)
print(json_str)
#{
# "x": 10,
# "y": 20,
# "nested": {
# "a": 30,
# "b": 40
# }
#}
# Deserialize from JSON
example_1 = JsonSerializer.loads(json_str, ExampleRec)
example_1.x += 1
example_1.y += 1
example_1.nested.a += 1
example_1.nested.b += 1
json_str = JsonSerializer.dumps(example_1)
print(json_str)
#{
# "x": 11,
# "y": 21,
# "nested": {
# "a": 31,
# "b": 41
# }
#}
这里给出的答案没有返回正确的对象类型，因此我在下面创建了这些方法。如果你试图向给定JSON中不存在的类中添加更多字段，它们也会失败:
def dict_to_class(class_name: Any, dictionary: dict) -> Any:
instance = class_name()
for key in dictionary.keys():
setattr(instance, key, dictionary[key])
return instance
def json_to_class(class_name: Any, json_string: str) -> Any:
dict_object = json.loads(json_string)
return dict_to_class(class_name, dict_object)
Dacite也可能是您的解决方案，它支持以下功能:
嵌套结构 (基本)类型检查 可选字段(即typing.Optional) 工会 向前引用 集合 自定义类型钩子
https://pypi.org/project/dacite/
from dataclasses import dataclass
from dacite import from_dict
@dataclass
class User:
name: str
age: int
is_active: bool
data = {
'name': 'John',
'age': 30,
'is_active': True,
}
user = from_dict(data_class=User, data=data)
assert user == User(name='John', age=30, is_active=True)
已经有多种可行的答案，但有一些由个人制作的小型库可以满足大多数用户的需求。
json2object就是一个例子。给定一个已定义的类，它将json数据反序列化到您的自定义模型，包括自定义属性和子对象。
它的使用非常简单。一个来自图书馆wiki的例子:
从json2object导入jsontoobject作为Jo 类学生: def __init__(自我): 自我。firstName =无 自我。lastName = None 自我。courses =[课程(")] 类课程: 定义__init__(self, name): Self.name = name 数据= " '{ “firstName”:“詹姆斯”, “姓”:“债券”, “课程”:[{ “名称”:“战斗”}, ｛ “名称”:“射击”} ］ } “‘ model = Student() Result = jo.deserialize(数据，模型) print (result.courses [0] . name)
我认为最简单的解决方法是
import orjson # faster then json =)
from typing import NamedTuple
_j = '{"name":"Иван","age":37,"mother":{"name":"Ольга","age":58},"children":["Маша","Игорь","Таня"],"married": true,' \
'"dog":null} '
class PersonNameAge(NamedTuple):
name: str
age: int
class UserInfo(NamedTuple):
name: str
age: int
mother: PersonNameAge
children: list
married: bool
dog: str
j = orjson.loads(_j)
u = UserInfo(**j)
print(u.name, u.age, u.mother, u.children, u.married, u.dog)
>>> Ivan 37 {'name': 'Olga', 'age': 58} ['Mary', 'Igor', 'Jane'] True None
JSON到python对象
下面的代码递归地使用对象键创建动态属性。
JSON对象- fb_data.json:
{
"name": "John Smith",
"hometown": {
"name": "New York",
"id": 123
},
"list": [
"a",
"b",
"c",
1,
{
"key": 1
}
],
"object": {
"key": {
"key": 1
}
}
}
在转换中我们有三种情况:
列表 Dicts(新对象) Bool, int, float和STR
import json
class AppConfiguration(object):
def __init__(self, data=None):
if data is None:
with open("fb_data.json") as fh:
data = json.loads(fh.read())
else:
data = dict(data)
for key, val in data.items():
setattr(self, key, self.compute_attr_value(val))
def compute_attr_value(self, value):
if isinstance(value, list):
return [self.compute_attr_value(x) for x in value]
elif isinstance(value, dict):
return AppConfiguration(value)
else:
return value
if __name__ == "__main__":
instance = AppConfiguration()
print(instance.name)
print(instance.hometown.name)
print(instance.hometown.id)
print(instance.list[4].key)
print(instance.object.key.key)
键值对是属性-对象。
输出:
John Smith
New York
123
1
1
将JSON作为代码粘贴
支持TypeScript、Python、Go、Ruby、c#、Java、Swift、Rust、Kotlin、c++、Flow、Objective-C、JavaScript、Elm、JSON Schema。
从JSON、JSON Schema和TypeScript中交互式地生成类型和(反)序列化代码 将JSON/JSON Schema/TypeScript作为代码粘贴
quicktype从示例JSON数据中推断类型，然后输出强类型模型和序列化器，以便用所需的编程语言处理这些数据。
输出:
# Generated by https://quicktype.io
#
# To change quicktype's target language, run command:
#
# "Set quicktype target language"
from typing import List, Union
class Hometown:
name: str
id: int
def __init__(self, name: str, id: int) -> None:
self.name = name
self.id = id
class Key:
key: int
def __init__(self, key: int) -> None:
self.key = key
class Object:
key: Key
def __init__(self, key: Key) -> None:
self.key = key
class FbData:
name: str
hometown: Hometown
list: List[Union[Key, int, str]]
object: Object
def __init__(self, name: str, hometown: Hometown, list: List[Union[Key, int, str]], object: Object) -> None:
self.name = name
self.hometown = hometown
self.list = list
self.object = object
这个扩展可以在Visual Studio代码市场中免费获得。
这不是一个很难的事情，我看到上面的答案，他们中的大多数在“列表”中有一个性能问题
这段代码比上面的代码快得多
import json
class jsonify:
def __init__(self, data):
self.jsonify = data
def __getattr__(self, attr):
value = self.jsonify.get(attr)
if isinstance(value, (list, dict)):
return jsonify(value)
return value
def __getitem__(self, index):
value = self.jsonify[index]
if isinstance(value, (list, dict)):
return jsonify(value)
return value
def __setitem__(self, index, value):
self.jsonify[index] = value
def __delattr__(self, index):
self.jsonify.pop(index)
def __delitem__(self, index):
self.jsonify.pop(index)
def __repr__(self):
return json.dumps(self.jsonify, indent=2, default=lambda x: str(x))
exmaple
response = jsonify(
{
'test': {
'test1': [{'ok': 1}]
}
}
)
response.test -> jsonify({'test1': [{'ok': 1}]})
response.test.test1 -> jsonify([{'ok': 1}])
response.test.test1[0] -> jsonify({'ok': 1})
response.test.test1[0].ok -> int(1)
class SimpleClass:
def __init__(self, **kwargs):
for k, v in kwargs.items():
if type(v) is dict:
setattr(self, k, SimpleClass(**v))
else:
setattr(self, k, v)
json_dict = {'name': 'jane doe', 'username': 'jane', 'test': {'foo': 1}}
class_instance = SimpleClass(**json_dict)
print(class_instance.name, class_instance.test.foo)
print(vars(class_instance))
这似乎是一个XY问题(问A实际问题在哪里B)。
问题的根源是:如何有效地引用/修改深嵌套的JSON结构，而不必做obj['foo']['bar'][42]['quux']，这带来了键入挑战，代码膨胀问题，可读性问题和错误捕获问题?
使用抢
from glom import glom
# Basic deep get
data = {'a': {'b': {'c': 'd'}}}
print(glom(data, 'a.b.c'))
它还将处理列表项:
我已经对一个简单的实现进行了基准测试:
def extract(J, levels):
# Twice as fast as using glom
for level in levels.split('.'):
J = J[int(level) if level.isnumeric() else level]
return J
．.． 并且在复杂的JSON对象上返回0.14ms，而朴素的impl则返回0.06ms。
它还可以处理复杂的查询，例如取出所有foo.bar.记录，其中.name == 'Joe Bloggs'
编辑:
另一种性能方法是递归地使用覆盖__getitem__和__getattr__的类:
class Ob:
def __init__(self, J):
self.J = J
def __getitem__(self, index):
return Ob(self.J[index])
def __getattr__(self, attr):
value = self.J.get(attr, None)
return Ob(value) if type(value) in (list, dict) else value
现在你可以做:
ob = Ob(J)
# if you're fetching a final raw value (not list/dict
ob.foo.bar[42].quux.leaf
# for intermediate values
ob.foo.bar[42].quux.J
这一基准测试也出奇地好。与我之前的天真冲动相当。如果有人能找到一种方法来整理非叶查询的访问，请留下评论!
数据类向导是一种现代的选项，可以类似地为您工作。它支持自动键大小写转换，如camelCase或TitleCase，这两者在API响应中都很常见。
当将实例转储到dict/JSON时，默认的键转换是camelCase，但这可以很容易地使用主数据类上提供的Meta配置来覆盖。
https://pypi.org/project/dataclass-wizard/
from dataclasses import dataclass
from dataclass_wizard import fromdict, asdict
@dataclass
class User:
name: str
age: int
is_active: bool
data = {
'name': 'John',
'age': 30,
'isActive': True,
}
user = fromdict(User, data)
assert user == User(name='John', age=30, is_active=True)
json_dict = asdict(user)
assert json_dict == {'name': 'John', 'age': 30, 'isActive': True}
设置元配置的例子，当序列化为dict/JSON时，将字段转换为lisp-case:
DumpMeta(key_transform='LISP').bind_to(User)
这是我的办法。
特性
支持类型提示 如果缺少键则引发错误。 跳过数据中的额外值
import typing
class User:
name: str
age: int
def __init__(self, data: dict):
for k, _ in typing.get_type_hints(self).items():
setattr(self, k, data[k])
data = {
"name": "Susan",
"age": 18
}
user = User(data)
print(user.name, user.age)
# Output: Susan 18
def load_model_from_dict(self, data: dict):
for key, value in data.items():
self.__dict__[key] = value
return self
它帮助返回你自己的模型，从字典中不可预见的变量。
因此，我正在寻找一种不需要大量自定义反序列化代码就能解组任意类型(想想数据类的字典，或者数据类数组的字典的字典)的方法。
这是我的方法:
import json
from dataclasses import dataclass, make_dataclass
from dataclasses_json import DataClassJsonMixin, dataclass_json
@dataclass_json
@dataclass
class Person:
name: str
def unmarshal_json(data, t):
Unmarhsal = make_dataclass('Unmarhsal', [('res', t)],
bases=(DataClassJsonMixin,))
d = json.loads(data)
out = Unmarhsal.from_dict({"res": d})
return out.res
unmarshalled = unmarshal_json('{"1": {"name": "john"} }', dict[str, Person])
print(unmarshalled)
打印:{'1':Person(name='john')}
如果你正在寻找将JSON或任何复杂字典的类型安全反序列化到python类中，我强烈推荐python 3.7+的pydantic。它不仅有一个简洁的API(不需要编写“helper”样板)，可以与Python数据类集成，而且具有复杂和嵌套数据结构的静态和运行时类型验证。
使用示例:
from pydantic import BaseModel
from datetime import datetime
class Item(BaseModel):
field1: str | int # union
field2: int | None = None # optional
field3: str = 'default' # default values
class User(BaseModel):
name: str | None = None
username: str
created: datetime # default type converters
items: list[Item] = [] # nested complex types
data = {
'name': 'Jane Doe',
'username': 'user1',
'created': '2020-12-31T23:59:00+10:00',
'items': [
{'field1': 1, 'field2': 2},
{'field1': 'b'},
{'field1': 'c', 'field3': 'override'}
]
}
user: User = User(**data)
要了解更多细节和特性，请查看文档中的pydantic的rational部分。
使用python 3.7，我发现下面的代码非常简单有效。在本例中，将JSON从文件加载到字典中:
class Characteristic:
def __init__(self, characteristicName, characteristicUUID):
self.characteristicName = characteristicName
self.characteristicUUID = characteristicUUID
class Service:
def __init__(self, serviceName, serviceUUID, characteristics):
self.serviceName = serviceName
self.serviceUUID = serviceUUID
self.characteristics = characteristics
class Definitions:
def __init__(self, services):
self.services = []
for service in services:
self.services.append(Service(**service))
def main():
parser = argparse.ArgumentParser(
prog="BLEStructureGenerator",
description="Taking in a JSON input file which lists all of the services, "
"characteristics and encoded properties. The encoding takes in "
"another optional template services and/or characteristics "
"file where the JSON file contents are applied to the templates.",
epilog="Copyright Brown & Watson International"
)
parser.add_argument('definitionfile',
type=argparse.FileType('r', encoding='UTF-8'),
help="JSON file which contains the list of characteristics and "
"services in the required format")
parser.add_argument('-s', '--services',
type=argparse.FileType('r', encoding='UTF-8'),
help="Services template file to be used for each service in the "
"JSON file list")
parser.add_argument('-c', '--characteristics',
type=argparse.FileType('r', encoding='UTF-8'),
help="Characteristics template file to be used for each service in the "
"JSON file list")
args = parser.parse_args()
definition_dict = json.load(args.definitionfile)
definitions = Definitions(**definition_dict)
