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?
当前回答
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
其他回答
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。
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。
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)
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)
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。
