此代码适用于任何给定的json文件

# -*- coding: utf-8 -*-
"""
Created on Mon Jun 17 20:35:35 2019
author: Ram
"""

import json
import csv

with open("file1.json") as file:
    data = json.load(file)



# create the csv writer object
pt_data1 = open('pt_data1.csv', 'w')
csvwriter = csv.writer(pt_data1)

count = 0

for pt in data:

      if count == 0:

             header = pt.keys()

             csvwriter.writerow(header)

             count += 1

      csvwriter.writerow(pt.values())

pt_data1.close()

我对丹提出的解决方案感到困惑，但这对我来说很管用:

import json
import csv 

f = open('test.json')
data = json.load(f)
f.close()

f=csv.writer(open('test.csv','wb+'))

for item in data:
  f.writerow([item['pk'], item['model']] + item['fields'].values())

“测试的地方。Json”包含以下内容:

[ 
{"pk": 22, "model": "auth.permission", "fields": 
  {"codename": "add_logentry", "name": "Can add log entry", "content_type": 8 } }, 
{"pk": 23, "model": "auth.permission", "fields": 
  {"codename": "change_logentry", "name": "Can change log entry", "content_type": 8 } }, {"pk": 24, "model": "auth.permission", "fields": 
  {"codename": "delete_logentry", "name": "Can delete log entry", "content_type": 8 } }
]

我假设您的JSON文件将解码为字典列表。首先，我们需要一个将JSON对象扁平化的函数:

def flattenjson(b, delim):
    val = {}
    for i in b.keys():
        if isinstance(b[i], dict):
            get = flattenjson(b[i], delim)
            for j in get.keys():
                val[i + delim + j] = get[j]
        else:
            val[i] = b[i]
            
    return val

在JSON对象上运行这段代码的结果:

flattenjson({
    "pk": 22, 
    "model": "auth.permission", 
    "fields": {
      "codename": "add_message", 
      "name": "Can add message", 
      "content_type": 8
    }
  }, "__")

is

{
    "pk": 22, 
    "model": "auth.permission", 
    "fields__codename": "add_message", 
    "fields__name": "Can add message", 
    "fields__content_type": 8
}

对JSON对象输入数组中的每个dict应用此函数后:

input = map(lambda x: flattenjson( x, "__" ), input)

并查找相关的列名:

columns = [x for row in input for x in row.keys()]
columns = list(set(columns))

在CSV模块中运行这个并不难:

with open(fname, 'wb') as out_file:
    csv_w = csv.writer(out_file)
    csv_w.writerow(columns)

    for i_r in input:
        csv_w.writerow(map(lambda x: i_r.get(x, ""), columns))

我可能迟到了，但我想，我已经处理过类似的问题。我有一个json文件，看起来像这样

我只想从这些json文件中提取一些键/值。因此，我编写了下面的代码来提取相同的内容。

    """json_to_csv.py
    This script reads n numbers of json files present in a folder and then extract certain data from each file and write in a csv file.
    The folder contains the python script i.e. json_to_csv.py, output.csv and another folder descriptions containing all the json files.
"""

import os
import json
import csv


def get_list_of_json_files():
    """Returns the list of filenames of all the Json files present in the folder
    Parameter
    ---------
    directory : str
        'descriptions' in this case
    Returns
    -------
    list_of_files: list
        List of the filenames of all the json files
    """

    list_of_files = os.listdir('descriptions')  # creates list of all the files in the folder

    return list_of_files


def create_list_from_json(jsonfile):
    """Returns a list of the extracted items from json file in the same order we need it.
    Parameter
    _________
    jsonfile : json
        The json file containing the data
    Returns
    -------
    one_sample_list : list
        The list of the extracted items needed for the final csv
    """

    with open(jsonfile) as f:
        data = json.load(f)

    data_list = []  # create an empty list

    # append the items to the list in the same order.
    data_list.append(data['_id'])
    data_list.append(data['_modelType'])
    data_list.append(data['creator']['_id'])
    data_list.append(data['creator']['name'])
    data_list.append(data['dataset']['_accessLevel'])
    data_list.append(data['dataset']['_id'])
    data_list.append(data['dataset']['description'])
    data_list.append(data['dataset']['name'])
    data_list.append(data['meta']['acquisition']['image_type'])
    data_list.append(data['meta']['acquisition']['pixelsX'])
    data_list.append(data['meta']['acquisition']['pixelsY'])
    data_list.append(data['meta']['clinical']['age_approx'])
    data_list.append(data['meta']['clinical']['benign_malignant'])
    data_list.append(data['meta']['clinical']['diagnosis'])
    data_list.append(data['meta']['clinical']['diagnosis_confirm_type'])
    data_list.append(data['meta']['clinical']['melanocytic'])
    data_list.append(data['meta']['clinical']['sex'])
    data_list.append(data['meta']['unstructured']['diagnosis'])
    # In few json files, the race was not there so using KeyError exception to add '' at the place
    try:
        data_list.append(data['meta']['unstructured']['race'])
    except KeyError:
        data_list.append("")  # will add an empty string in case race is not there.
    data_list.append(data['name'])

    return data_list


def write_csv():
    """Creates the desired csv file
    Parameters
    __________
    list_of_files : file
        The list created by get_list_of_json_files() method
    result.csv : csv
        The csv file containing the header only
    Returns
    _______
    result.csv : csv
        The desired csv file
    """

    list_of_files = get_list_of_json_files()
    for file in list_of_files:
        row = create_list_from_json(f'descriptions/{file}')  # create the row to be added to csv for each file (json-file)
        with open('output.csv', 'a') as c:
            writer = csv.writer(c)
            writer.writerow(row)
        c.close()


if __name__ == '__main__':
    write_csv()

我希望这能有所帮助。有关此代码如何工作的详细信息，请查看这里

使用pandas中的json_normalize:

在名为test.json的文件中使用来自OP的示例数据。 这里使用了Encoding ='utf-8'，但在其他情况下可能不需要。 下面的代码利用了pathlib库。 .open是pathlib的一个方法。 也适用于非windows路径。 使用pandas.to_csv(…)将数据保存为csv文件。

import pandas as pd
# As of Pandas 1.01, json_normalize as pandas.io.json.json_normalize is deprecated and is now exposed in the top-level namespace.
# from pandas.io.json import json_normalize
from pathlib import Path
import json

# set path to file
p = Path(r'c:\some_path_to_file\test.json')

# read json
with p.open('r', encoding='utf-8') as f:
    data = json.loads(f.read())

# create dataframe
df = pd.json_normalize(data)

# dataframe view
 pk            model  fields.codename           fields.name  fields.content_type
 22  auth.permission     add_logentry     Can add log entry                    8
 23  auth.permission  change_logentry  Can change log entry                    8
 24  auth.permission  delete_logentry  Can delete log entry                    8
  4  auth.permission        add_group         Can add group                    2
 10  auth.permission      add_message       Can add message                    4

# save to csv
df.to_csv('test.csv', index=False, encoding='utf-8')

CSV输出:

pk,model,fields.codename,fields.name,fields.content_type
22,auth.permission,add_logentry,Can add log entry,8
23,auth.permission,change_logentry,Can change log entry,8
24,auth.permission,delete_logentry,Can delete log entry,8
4,auth.permission,add_group,Can add group,2
10,auth.permission,add_message,Can add message,4

嵌套更重的JSON对象的资源:

所以答案: 用python平化JSON数组 如何平嵌套的JSON递归，与平坦JSON 如何json_normalize一个列与nan 使用pandas将一列字典拆分为单独的列 有关其他相关问题，请参阅json_normalize标记。

使用pandas库，这就像使用两个命令一样简单!

df = pd.read_json()

read_json将JSON字符串转换为pandas对象(序列或数据帧)。然后:

df.to_csv()

它既可以返回字符串，也可以直接写入csv文件。请参阅to_csv的文档。

根据之前的冗长回答，我们都应该感谢熊猫提供的这条捷径。

关于非结构化JSON，请参阅这个答案。

编辑: 有人问我一个最小的例子:

import pandas as pd

with open('jsonfile.json', encoding='utf-8') as inputfile:
    df = pd.read_json(inputfile)

df.to_csv('csvfile.csv', encoding='utf-8', index=False)