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
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。
其他回答
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。
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)
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)
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
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。
