Python 可序列化对象 json

Question

class gpagelet:
    """
    Holds   1) the pagelet xpath, which is a string
            2) the list of pagelet shingles, list
    """
    def __init__(self, parent):
        if not isinstance( parent, gwebpage):
            raise Exception("Parent must be an instance of gwebpage")
        self.parent = parent    # This must be a gwebpage instance
        self.xpath = None       # String
        self.visibleShingles = [] # list of tuples
        self.invisibleShingles = [] # list of tuples
        self.urls = [] # list of string

class gwebpage:
    """
    Holds all the datastructure after the results have been parsed
    holds:  1) lists of gpagelets
            2) loc, string, location of the file that represents it
    """
    def __init__(self, url):
        self.url = url              # Str
        self.netloc = False         # Str
        self.gpagelets = []         # gpagelets instance
        self.page_key = ""          # str

有没有办法让我的类 json 可序列化？我担心的是递归引用。

Answer 1

编写自己的编码器和解码器，可以很简单，比如return __dict__

例如这是一个转储完全递归树结构的编码器，您可以对其进行增强或将其用于您自己的目的

import json

class Tree(object):
    def __init__(self, name, childTrees=None):
        self.name = name
        if childTrees is None:
            childTrees = []
        self.childTrees = childTrees

class MyEncoder(json.JSONEncoder):
    def default(self, obj):
        if not isinstance(obj, Tree):
            return super(MyEncoder, self).default(obj)

        return obj.__dict__

c1 = Tree("c1")
c2 = Tree("c2") 
t = Tree("t",[c1,c2])

print json.dumps(t, cls=MyEncoder)

打印出来

{"childTrees": [{"childTrees": [], "name": "c1"}, {"childTrees": [], "name": "c2"}], "name": "t"}

你可以类似地编写一个解码器，但你需要以某种方式确定它是否是你的对象，所以如果需要你也可以输入一个类型。

Answer 2

间接回答：您可以使用YAML，而不是使用 JSON，这可以满足您的需求。 （JSON 本质上是 YAML 的一个子集。）

例子：

import yaml
o1 = gwebpage("url")
o2 = gpagelet(o1)
o1.gpagelets = [o2]
print yaml.dump(o1)

事实上，YAML 可以很好地为您处理循环引用。

Answer 3

我在https://stackoverflow.com/a/11637457/1766716的帮助下实现了一个非常简单的todict方法

• 迭代不是以__ 开头的属性
• 消除方法
• 手动消除一些不必要的属性（对于我来说，来自 sqlalcemy）

并使用getattr构建字典。

class User(Base):
    id = Column(Integer, primary_key=True)
    firstname = Column(String(50))
    lastname = Column(String(50))
    password = Column(String(20))
    def props(self):
        return filter(
            lambda a:
            not a.startswith('__')
            and a not in ['_decl_class_registry', '_sa_instance_state', '_sa_class_manager', 'metadata']
            and not callable(getattr(self, a)),
            dir(self))
    def todict(self):
        return {k: self.__getattribute__(k) for k in self.props()}

Answer 4

对此我的解决方案是扩展“dict”类，并通过覆盖 init、update 和 set 类方法来检查所需/允许的属性。

class StrictDict(dict):
    required=set()
    at_least_one_required=set()
    cannot_coexist=set()
    allowed=set()
    def __init__(self, iterable={}, **kwargs):
        super(StrictDict, self).__init__({})
        keys = set(iterable.keys()).union(set(kwargs.keys()))
        if not keys.issuperset(self.required):
            msg = str(self.__class__.__name__) + " requires: " + str([str(key) for key in self.required])
            raise AttributeError(msg)
        if len(list(self.at_least_one_required)) and len(list(keys.intersection(self.at_least_one_required))) < 1:
            msg = str(self.__class__.__name__) + " requires at least one: " + str([str(key) for key in self.at_least_one_required])
            raise AttributeError(msg)
        for key, val in iterable.iteritems():
            self.__setitem__(key, val)
        for key, val in kwargs.iteritems():
            self.__setitem__(key, val)

    def update(self, E=None, **F):
        for key, val in E.iteritems():
            self.__setitem__(key, val)
        for key, val in F.iteritems():
            self.__setitem__(key, val)
        super(StrictDict, self).update({})

    def __setitem__(self, key, value):
        all_allowed = self.allowed.union(self.required).union(self.at_least_one_required).union(self.cannot_coexist)
        if key not in list(all_allowed):
            msg = str(self.__class__.__name__) + " does not allow member '" + key + "'"
            raise AttributeError(msg)
        if key in list(self.cannot_coexist):
            for item in list(self.cannot_coexist):
                if key != item and item in self.keys():
                    msg = str(self.__class__.__name__) + "does not allow members '" + key + "' and '" + item + "' to coexist'"
                    raise AttributeError(msg)
        super(StrictDict, self).__setitem__(key, value)

示例用法：

class JSONDoc(StrictDict):
    """
    Class corresponding to JSON API top-level document structure
    http://jsonapi.org/format/#document-top-level
    """
    at_least_one_required={'data', 'errors', 'meta'}
    allowed={"jsonapi", "links", "included"}
    cannot_coexist={"data", "errors"}
    def __setitem__(self, key, value):
        if key == "included" and "data" not in self.keys():
            msg = str(self.__class__.__name__) + " does not allow 'included' member if 'data' member is not present"
            raise AttributeError(msg)
        super(JSONDoc, self).__setitem__(key, value)

json_doc = JSONDoc(
    data={
        "id": 5,
        "type": "movies"
    },
    links={
        "self": "http://url.com"
    }
)