Python 解析库json及jsonpath pickle的实现

1. 数据抽取的概念

3. JSON数据概述及解析

3.1 JSON数据格式

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"]()

JsonPath与XPath语法对比：

Json结构清晰，可读性高，复杂度低，非常容易匹配，下表中对应了XPath的用法。

到此这篇关于Python 解析库json及jsonpath pickle的实现的文章就介绍到这了,更多相关Python 解析库json及jsonpath pickle内容请搜索来客网以前的文章或继续浏览下面的相关文章希望大家以后多多支持来客网！