1. 数据抽取的概念

2. 数据的分类

3. JSON数据概述及解析

3.1 JSON数据格式

3.2 解析库json

json模块是Python内置标准库，主要可以完成两个功能：序列化和反序列化。JSON对象和Python对象映射图如下：

3.2.1 json序列化

对象(字典/列表) 通过 json.dump()/json.dumps() ==> json字符串。示例代码如下：

import json


class Phone(object):
    def __init__(self, name, price):
        self.name = name
        self.price = price


class Default(json.JSONEncoder):
    def default(self, o):
        print(o)  # o: <__main__.Phone object at 0x10aa52c90>
        return [o.name, o.price]


def parse(obj):
    print(obj)
    return {"name": obj.name, "price": obj.price}


person_info_dict = {
    "name": "Amo",
    "age": 18,
    "is_boy": True,
    # "n": float("nan"),  # float("nan"):NaN float("inf")=>Infinity float("-inf")=>-Infinity
    "phone": Phone("苹果8plus", 6458),
    "hobby": ("sing", "dance"),
    "dog": {
        "name": "藏獒",
        "age": 5,
        "color": "棕色",
        "isVIP": True,
        "child": None
    },
}

"""
obj:需要序列化的对象 字典/列表 这里指的是person_info_dict
indent: 缩进 单位: 字符
sort_keys: 是否按key排序 默认是False不排序
cls: json.JSONEncoder子类 处理不能序列化的对象
ensure_ascii: 是否确保ascii编码 默认是True确保 "苹果8plus"==>"\u82f9\u679c8plus" 所以改为False
default: 对象不能被序列化时，调用对应的函数解析
"""

# 将结果返回给一个变量
result = json.dumps(person_info_dict,
                    indent=2,
                    sort_keys=True,
                    ensure_ascii=False,
                    # cls=Default,
                    default=parse,
                    # allow_nan=False 是否处理特殊常量值
                    # 默认为True 但是JSON标准规范不支持NaN, Infinity和-Infinity
                    )
print(result)
with open("dump.json", "w", encoding="utf8") as file:
    # json.dump是将序列化后的内容存储到文件中 其他参数用法和dumps一致
    json.dump(person_info_dict, file, indent=4, ensure_ascii=False, default=parse)

3.2.2 json反序列化

json字符串通过json.load()/json.loads()==> 对象(字典/列表)，示例代码如下：

import json


class Phone(object):
    def __init__(self, name, price):
        self.name = name
        self.price = price


def pi(num):
    return int(num) + 1


def oh(dic):
    if "price" in dic.keys():
        return Phone(dic["name"], dic["price"])
    return dic


def oph(*args, **kwargs):
    print(*args, **kwargs)


# 我自己本地有一个dump.json文件
with open("dump.json", "r", encoding="utf8") as file:
    # content = file.read()
    # parse_int/float: 整数/浮点数钩子函数
    # object_hook: 对象解析钩子函数 将字典转为特定对象 传递给函数的是字典对象
    # object_pairs_hook: 转化为特定对象 传递的是元组列表
    # parse_constant: 常量钩子函数 NaN/Infinity/-Infinity
    # result = json.loads(content, object_hook=oh, parse_int=pi, object_pairs_hook=oph)
    result = json.load(file, parse_int=pi, object_hook=oh)  # 直接将文件对象传入
    print(type(result))  # <class 'dict'>
    print(result)

4. jsonpath

jsonpath三方库，点击这里这里进入官网，通过路径表达式，来快速获取字典当中的指定数据，灵感来自xpath表达式。命令安装：

pip install --user -i http://pypi.douban.com/simple --trusted-host pypi.douban.com jsonpath

或者：

4.1 使用

语法格式如下：

from jsonpath import jsonpath
dic = {....}  # 要找数据的字典
jsonpath(dic, 表达式)

常用的表达式语法如下：

4.2 使用示例

案例一用到的字典如下：

dic = {
    "person": {
        "name": "Amo",
        "age": 18,
        "dog": [{
            "name": "小花",
            "color": "red",
            "age": 6,
            "isVIP": True
        },
            {
                "name": "小黑",
                "color": "black",
                "age": 2
            }]
    }
}

将上述抽象成一个树形结构如图所示：

需求及结果如下：

代码如下：

from jsonpath import jsonpath

dic = {
    "person": {
        "name": "Amo",
        "age": 18,
        "dog": [{
            "name": "小花",
            "color": "red",
            "age": 6,
            "isVIP": True
        },
            {
                "name": "小黑",
                "color": "black",
                "age": 2
            }]
    }
}

# 1.获取人的年龄
print(jsonpath(dic, "$.person.age"))  # 获取到数据返回一个列表 否则返回False
# 2.获取第2个小狗的年龄
print(jsonpath(dic, "$..dog[1].age"))
# 3.获取所有小狗的年龄
print(jsonpath(dic, "$..dog[0,1].age"))
print(jsonpath(dic, "$..dog[*].age"))
# 4.获取是VIP的小狗
print(jsonpath(dic, "$..dog[?(@.isVIP)]"))
# 5.获取年龄大于2的小狗
print(jsonpath(dic, "$..dog[?(@.age>2)]"))
# 6.获取最后一个小狗
print(jsonpath(dic, "$..dog[-1:]"))
print(jsonpath(dic, "$..dog[(@.length-1)]"))

上述代码执行结果如下：

案例二用到的字典如下：

book_dict = {
    "store": {
        "book": [
            {"category": "reference",
             "author": "Nigel Rees",
             "title": "Sayings of the Century",
             "price": 8.95
             },
            {"category": "fiction",
             "author": "Evelyn Waugh",
             "title": "Sword of Honour",
             "price": 12.99
             },
            {"category": "fiction",
             "author": "Herman Melville",
             "title": "Moby Dick",
             "isbn": "0-553-21311-3",
             "price": 8.99
             },
            {"category": "fiction",
             "author": "J. R. R. Tolkien",
             "title": "The Lord of the Rings",
             "isbn": "0-395-19395-8",
             "price": 22.99
             }
        ],
        "bicycle": {
            "color": "red",
            "price": 19.95
        }
    }
}

将上述抽象成一个树形结构如图所示：

需求及结果如下：

代码如下：

from jsonpath import jsonpath

book_dict = {
    "store": {
        "book": [
            {"category": "reference",
             "author": "Nigel Rees",
             "title": "Sayings of the Century",
             "price": 8.95
             },
            {"category": "fiction",
             "author": "Evelyn Waugh",
             "title": "Sword of Honour",
             "price": 12.99
             },
            {"category": "fiction",
             "author": "Herman Melville",
             "title": "Moby Dick",
             "isbn": "0-553-21311-3",
             "price": 8.99
             },
            {"category": "fiction",
             "author": "J. R. R. Tolkien",
             "title": "The Lord of the Rings",
             "isbn": "0-395-19395-8",
             "price": 22.99
             }
        ],
        "bicycle": {
            "color": "red",
            "price": 19.95
        }
    }
}
# 1.store中的所有的book的作者
print(jsonpath(book_dict, "$.store.book[*].author"))
print(jsonpath(book_dict, "$..author"))
# 2.store下的所有的元素
print(jsonpath(book_dict, "$.store[*]"))
print(jsonpath(book_dict, "$.store.*"))
# 3.store中的所有的内容的价格
print(jsonpath(book_dict, "$..price"))
# 4.第三本书
print(jsonpath(book_dict, "$..book[2]"))
# 5.最后一本书
print(jsonpath(book_dict, "$..book[-1:]"))
print(jsonpath(book_dict, "$..book[(@.length-1)]"))
# 6.前两本书
print(jsonpath(book_dict, "$..book[0:2]"))
# 7.获取有isbn的所有书
print(jsonpath(book_dict, "$.store.book[?(@.isbn)]"))
# 8.获取价格大于10的所有的书
print(jsonpath(book_dict, "$.store.book[?(@.price>10)]"))
# 9.获取所有的数据
print(jsonpath(book_dict, "$..*"))

5. Python专用JSON解析库pickle

pickle处理的json对象不通用，可以额外的把函数给序列化。示例代码如下：

import pickle


def eat():
    print("Amo在努力地写博客~")


person_info_dict = {
    "name": "Amo",
    "age": 18,
    "eat": eat
}

# print(pickle.dumps(person_info_dict))
with open("pickle_json", "wb") as file:
    pickle.dump(person_info_dict, file)

with open("pickle_json", "rb") as file:
    result = pickle.load(file)
    result["eat"]()