简单介绍Python中的JSON模块

import json

json.dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True,cls=None, indent=None, separators=None, encoding="utf-8", default=None, sort_keys=False,**kw)

obj = [[1,2,3],123,123.123,'abc',{'key1':(1,2,3),'key2':(4,5,6)}] 
encodedjson = json.dumps(obj) 
print 'the original list:\n',obj 
print 'length of obj is:',len(repr(obj))
print 'repr(obj),replace whiteblank with *:\n', repr(obj).replace(' ','*') 
print 'json encoded,replace whiteblank with *:\n',encodedjson.replace(' ','*')

the original list: 
[[1, 2, 3], 123, 123.123, 'abc', {'key2': (4, 5, 6), 'key1': (1, 2, 3)}] 
length of obj is: 72
repr(obj),replace whiteblank with *: 
[[1,*2,*3],*123,*123.123,*'abc',*{'key2':*(4,*5,*6),*'key1':*(1,*2,*3)}] 
json encoded,replace whiteblank with *: 
[[1,*2,*3],*123,*123.123,*"abc",*{"key2":*[4,*5,*6],*"key1":*[1,*2,*3]}] 
<type 'list'>

decodejson = json.loads(encodedjson) 
print 'the type of decodeed obj from json:', type(decodejson) 
print 'the obj is:\n',decodejson 
print 'length of decoded obj is:',len(repr(decodejson))

the type of decodeed obj from json: <type 'list'> 
the obj is: 
[[1, 2, 3], 123, 123.123, u'abc', {u'key2': [4, 5, 6], u'key1': [1, 2, 3]}] 
length of decoded obj is: 75 #比原obj多出了3个unicode编码标示‘u'

data1 = {'b':789,'c':456,'a':123} 
data2 = {'a':123,'b':789,'c':456} 
d1 = json.dumps(data1,sort_keys=True) 
d2 = json.dumps(data2) 
d3 = json.dumps(data2,sort_keys=True) 
print 'sorted data1(d1):',d1 
print 'unsorted data2(d2):',d2 
print 'sorted data2(d3):',d3 
print 'd1==d2"htmlcode">

sorted data1(d1): {"a": 123, "b": 789, "c": 456} 
unsorted data2(d2): {"a": 123, "c": 456, "b": 789} 
sorted data2(d3): {"a": 123, "b": 789, "c": 456} 
d1==d2"htmlcode">

data = {'b':789,'c':456,'a':123} 
d1 = json.dumps(data,sort_keys=True,indent=4) 
print 'data len is:',len(repr(data)) 
print '4 indented data:\n',d1 
d2 = json.loads(d1) 
print 'decoded DATA:', repr(d2) 
print 'len of decoded DATA:',len(repr(d2))



输出：（可见loads时会将dumps时增加的intent 填充空格去除）

 




data len is: 30 
4 indented data: 
{ 
  "a": 123,  
  "b": 789,  
  "c": 456 
} 
decoded DATA: {u'a': 123, u'c': 456, u'b': 789} 
len of decoded DATA: 33



json主要是作为一种数据通信的格式存在的，无用的空格会浪费通信带宽，适当时候也要对数据进行压缩。separator参数可以起到这样的作用，该参数传递是一个元组，包含分割对象的字符串，其实质就是将Python默认的（‘, ',': '）分隔符替换成（',',':'）。

 




data = {'b':789,'c':456,'a':123} 
print 'DATA:', repr(data) 
print 'repr(data)       :', len(repr(data)) 
print 'dumps(data)      :', len(json.dumps(data)) 
print 'dumps(data, indent=2) :', len(json.dumps(data, indent=4)) 
print 'dumps(data, separators):', len(json.dumps(data, separators=(',',':')))



输出:

 




DATA: {'a': 123, 'c': 456, 'b': 789} 
repr(data)       : 30 
dumps(data)      : 30 
dumps(data, indent=2) : 46 
dumps(data, separators): 25





另一个比较有用的dumps参数是skipkeys，默认为False。 dumps方法存储dict对象时key必须是str类型，其他类型会导致TypeError异常产生，如果将skipkeys设为True则会优雅的滤除非法keys。

 




data = {'b':789,'c':456,(1,2):123} 
print'original data:',repr(data) 
print 'json encoded',json.dumps(data,skipkeys=True)



输出:

 




original data: {(1, 2): 123, 'c': 456, 'b': 789} 
json encoded {"c": 456, "b": 789}



2，JSON处理自定义数据类型
json模块不仅可以处理普通的python内置类型，也可以处理我们自定义的数据类型，而往往处理自定义的对象是很常用的。
如果直接通过json.dumps方法对Person的实例进行处理的话，会报错，因为json无法支持这样的自动转化。通过上面所提到的json和 python的类型转化对照表，可以发现，object类型是和dict相关联的，所以我们需要把我们自定义的类型转化为dict，然后再进行处理。这里，有两种方法可以使用。
方法一：自己写转化函数
自定义object类型和dict类型进行转化：encode-定义函数 object2dict()将对象模块名、类名以及__dict__存储在一个字典并返回;decode-定义dict2object()解析出模块名、类名、参数，创建新的对象并返回。在json.dumps()中通过default参数指定转化过程中调用的函数；json.loads()则通过 object_hook指定转化函数。
方法二：继承JSONEncoder和JSONDecoder类，覆写相关方法
JSONEncoder类负责编码，主要是通过其default函数进行转化，我们可以重载该方法。对于JSONDecoder，亦然。


#handling private data type 
#define class 
class Person(object): 
  def __init__(self,name,age): 
    self.name = name 
    self.age = age 
  def __repr__(self): 
    return 'Person Object name : %s , age : %d' % (self.name,self.age) 
    
    
#define transfer functions 
def object2dict(obj): 
  #convert object to a dict 
  d = {'__class__':obj.__class__.__name__, '__module__':obj.__module__} 
  d.update(obj.__dict__) 
  return d 
   
def dict2object(d): 
  #convert dict to object 
  if'__class__' in d: 
    class_name = d.pop('__class__') 
    module_name = d.pop('__module__') 
    module = __import__(module_name) 
    print 'the module is:', module 
    class_ = getattr(module,class_name) 
    args = dict((key.encode('ascii'), value) for key, value in d.items()) #get args 
    print 'the atrribute:', repr(args) 
    inst = class_(**args) #create new instance 
  else: 
    inst = d 
  return inst 
#recreate the default method 
class LocalEncoder(json.JSONEncoder): 
  def default(self,obj): 
    #convert object to a dict 
    d = {'__class__':obj.__class__.__name__, '__module__':obj.__module__} 
    d.update(obj.__dict__) 
    return d 
   
class LocalDecoder(json.JSONDecoder): 
  def __init__(self): 
    json.JSONDecoder.__init__(self,object_hook = self.dict2object) 
  def dict2object(self, d): 
    #convert dict to object 
    if'__class__' in d: 
      class_name = d.pop('__class__') 
      module_name = d.pop('__module__') 
      module = __import__(module_name) 
      class_ = getattr(module,class_name) 
      args = dict((key.encode('ascii'), value) for key, value in d.items()) #get args 
      inst = class_(**args) #create new instance 
    else: 
      inst = d 
    return inst 
#test function 
if __name__ == '__main__': 
  p = Person('Aidan',22) 
  print p 
  #json.dumps(p)#error will be throwed 
  d = object2dict(p) 
  print 'method-json encode:', d 
   
  o = dict2object(d) 
  print 'the decoded obj type: %s, obj:%s' % (type(o),repr(o)) 
   
  dump = json.dumps(p,default=object2dict) 
  print 'dumps(default = object2dict):',dump 
  load = json.loads(dump,object_hook = dict2object) 
  print 'loads(object_hook = dict2object):',load 
  d = LocalEncoder().encode(p) 
  o = LocalDecoder().decode(d) 
   
  print 'recereated encode method: ',d 
  print 'recereated decode method: ',type(o),o




输出：




Person Object name : Aidan , age : 22 
method-json encode: {'age': 22, '__module__': '__main__', '__class__': 'Person', 'name': 'Aidan'} 
the module is: <module '__main__' from 'D:/Project/Python/study_json'> 
the atrribute: {'age': 22, 'name': 'Aidan'} 
the decoded obj type: <class '__main__.Person'>, obj:Person Object name : Aidan , age : 22 
dumps(default = object2dict): {"age": 22, "__module__": "__main__", "__class__": "Person", "name": "Aidan"} 
the module is: <module '__main__' from 'D:/Project/Python/study_json'> 
the atrribute: {'age': 22, 'name': u'Aidan'} 
loads(object_hook = dict2object): Person Object name : Aidan , age : 22 
recereated encode method: {"age": 22, "__module__": "__main__", "__class__": "Person", "name": "Aidan"} 
recereated decode method: <class '__main__.Person'> Person Object name : Aidan , age : 22