JSON格式

JSON (JavaScript Object Notation)
JSON语法规则
- 名称必须用双引号括起来
- 值可以是任意的由双引号包括的字符串、数字、布尔值、空值、JavaScript数组
- 数据间用逗号分隔
- 花括号用于保存对象
- 方括号用于保存数组
JSON数据类型与Python的对照

Python	JSON
dict	object
list, tuple	array
str, unicode	string
int, long, float	number
True	true
False	false
None	null

Python中的JSON

将Python对象编码成json字符串 dumps()
- 他会自动调整格式

import json
data = {'name':'eric','id':1001}
print(json.dumps(data))

{"name": "eric", "id": 1001}

将json字符串解码Python对像 loads()
字典

import json
data = {'name':'eric','id':1001}
a = json.dumps(data)
print(json.loads(a))

{'name': 'eric', 'id': 1001}

元组和列表
- 都会转换成列表或者array的形式

import json
data1 = ("eric","is","old","involation","dog")
data2 = ["eric","is","old","involation","dog"]

j1 = json.dumps(data1)
j2 = json.dumps(data2)

print(j1,end=" this is j1\n")
print(j2,end=" this is j2\n")

a1 = json.loads(j1)
a2 = json.loads(j2)

print(a1,end=" this is a1\n")
print(a2,end=" this is a2\n")

###
["eric", "is", "old", "involation", "dog"] this is j1
["eric", "is", "old", "involation", "dog"] this is j2
['eric', 'is', 'old', 'involation', 'dog'] this is a1
['eric', 'is', 'old', 'involation', 'dog'] this is a2

将Python序列转换为json对象后写入文件 dump()

import json
 
data = {
    'name':'eric',
    'F1':["is","old","involation"],
    'F2':("dog","hahaha","just joke")}

with open('json_test.txt','w+') as f:
    json.dump(data,f)

##文件中的内容
{"name": "eric", "F1": ["is", "old", "involation"], "F2": ["dog", "hahaha", "just joke"]}

读取文件中的json文件字符串元素转换为Python类型 load()

import json
data = {
    'id':'202101',
    'a':["足"，"力","健"],
    'b':("老","人","鞋")
}

with open('json_test.txt','w+') as f:
    json.dump(data,f)
with open('json_test.txt','r+') as f:
    print(json.load(f))

{'id': '202101', 'a': ['足', '力', '健'], 'b': ['老', '人', '鞋']}

python的unicode字符串转换为json的字符串

>>> json.dumps(u"a")
'"a"'

查看json的类型

>>> type(json.dumps("abc"))
<class 'str'>

dumps参数详解

dumps(obj,skipkeys=False, 
      ensure_ascii=True, 
      check_circular=True,
      allow_nan=True, 
      separators=None,
      default=None, 
      sort_keys=False, **kw):

skipkeys：	如果为True的话，则只能是字典对象
ensure_ascii	确定是否为ASCII编码
check_circular	为True 循环类型检查
allow_nan	是否为允许空值
separators	对象分隔符
sort_keys	True的话，对于字典类型会按照键的ASCII码来排序

dump参数详解
- 增加了一个文件对象，保存信息，很容易理解
JSON到对象

import json
from faker import Faker

A = Faker(locale="zh_CN")

class Employee():
      def __init__(self,name,tel):
            self.name=name
            self.tel=tel
            
B = Employee(A.name(),A.phone_number())

def jsonToClass(B):
      return Employee(B['name'],B['tel'])
    
json_str = '{"name": "Harry Potter","tel":8888888888}'
B = json.loads(json_str, object_hook=jsonToClass)
print(B)
print(B.name)

CSV格式

Comma-Separated Values CSV的含义

内置库csv按行读取

import csv
data = []
with open("a.txt","r") as file:
    lines = csv.reader(file)
    for line in lines:
        data.append(line)

print(data)

[['1', '2', '3', '4', '5', '6', '7', '8', '9'], ['11', '12', '13', '14', '15', '16', '17', '18', '19'], ['11', '12', '13', '14', '15', '16', '17', '18', '19'], ['11', '12', '13', '14', '15', '16', '17', '18', '19'], ['11', '12', '13', '14', '15', '16', '17', '18', '19'], ['1', '2', '3', '4', '5', '6', '7', '8', '9'], ['1', '2', '3', '4', '5', '6', '7', '8', '9'], ['1', '2', '3', '4', '5', '6', '7', '8', '9']]

pandas读取

import pandas as pd
data = pd.read_csv("a.txt",header = None)
print(data)
print("!!!###!!!")
data = pd.read_csv("a.txt")
print(data)

    0   1   2   3   4   5   6   7   8
0   1   2   3   4   5   6   7   8   9
1  11  12  13  14  15  16  17  18  19
2  11  12  13  14  15  16  17  18  19
3  11  12  13  14  15  16  17  18  19
4  11  12  13  14  15  16  17  18  19
5   1   2   3   4   5   6   7   8   9
6   1   2   3   4   5   6   7   8   9
7   1   2   3   4   5   6   7   8   9
!!!###!!!
    1   2   3   4   5   6   7   8   9
0  11  12  13  14  15  16  17  18  19
1  11  12  13  14  15  16  17  18  19
2  11  12  13  14  15  16  17  18  19
3  11  12  13  14  15  16  17  18  19
4   1   2   3   4   5   6   7   8   9
5   1   2   3   4   5   6   7   8   9
6   1   2   3   4   5   6   7   8   9

numpy包读取

from numpy import genfromtxt
filename = "a"
filetype = ".txt"

#delimiter  分隔符
data = genfromtxt(filename+filetype, delimiter=',')
print(data)

[[ 1.  2.  3.  4.  5.  6.  7.  8.  9.]
 [11. 12. 13. 14. 15. 16. 17. 18. 19.]
 [11. 12. 13. 14. 15. 16. 17. 18. 19.]
 [11. 12. 13. 14. 15. 16. 17. 18. 19.]
 [11. 12. 13. 14. 15. 16. 17. 18. 19.]
 [ 1.  2.  3.  4.  5.  6.  7.  8.  9.]
 [ 1.  2.  3.  4.  5.  6.  7.  8.  9.]
 [ 1.  2.  3.  4.  5.  6.  7.  8.  9.]]

dat文件

from 百度：
- .dat并不是一种标准文件。许多文件都使用这个扩展名，但文件含义不同。而许多数据分析软件也用这个扩展名保存数据。所以这要看具体的软件情况来定。DAT文件，可以按照扩展名来看就是DATA的意思，即数据文件，这类文件并没有进行绝对化的定义

import numpy as np
filename = "a"
filetype = ".dat"

data = np.fromfile(filename+filetype)
print(data)

也许你很少用到dat文件
- 但是你需要知道，直接改个后缀是不能直接改变文件格式的，至少大多数情况下如此

Python 常用的数据格式

JSON格式

Python中的JSON

CSV格式

内置库csv按行读取

pandas读取

numpy包读取

dat文件

CSON格式

Protobuf协议

properties

yaml

toml

XML文本标记语言

猜你喜欢