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

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))

解决这个问题的简单方法是:

创建一个新的Python文件，如:json_to_csv.py

添加以下代码:

import csv, json, sys
#if you are not using utf-8 files, remove the next line
sys.setdefaultencoding("UTF-8")
#check if you pass the input file and output file
if sys.argv[1] is not None and sys.argv[2] is not None:

    fileInput = sys.argv[1]
    fileOutput = sys.argv[2]

    inputFile = open(fileInput)
    outputFile = open(fileOutput, 'w')
    data = json.load(inputFile)
    inputFile.close()

    output = csv.writer(outputFile)

    output.writerow(data[0].keys())  # header row

    for row in data:
        output.writerow(row.values())

添加代码后，保存文件并在终端上运行:

Python json_to_csv.py input.txt output.csv

我希望这对你有帮助。

韩国歌手组合!

如果我们考虑下面的例子，将json格式的文件转换为csv格式的文件。

{
 "item_data" : [
      {
        "item": "10023456",
        "class": "100",
        "subclass": "123"
      }
      ]
}

下面的代码将转换json文件(data3. xml)。Json)转换为CSV文件(data3.csv)。

import json
import csv
with open("/Users/Desktop/json/data3.json") as file:
    data = json.load(file)
    file.close()
    print(data)

fname = "/Users/Desktop/json/data3.csv"

with open(fname, "w", newline='') as file:
    csv_file = csv.writer(file)
    csv_file.writerow(['dept',
                       'class',
                       'subclass'])
    for item in data["item_data"]:
         csv_file.writerow([item.get('item_data').get('dept'),
                            item.get('item_data').get('class'),
                            item.get('item_data').get('subclass')])

上面提到的代码已经在本地安装的pycharm中执行，它已经成功地将json文件转换为csv文件。希望这有助于转换文件。

这是@MikeRepass回答的修改。此版本将CSV写入文件，适用于Python 2和Python 3。

import csv,json
input_file="data.json"
output_file="data.csv"
with open(input_file) as f:
    content=json.load(f)
try:
    context=open(output_file,'w',newline='') # Python 3
except TypeError:
    context=open(output_file,'wb') # Python 2
with context as file:
    writer=csv.writer(file)
    writer.writerow(content[0].keys()) # header row
    for row in content:
        writer.writerow(row.values())

import json,csv
t=''
t=(type('a'))
json_data = []
data = None
write_header = True
item_keys = []
try:
with open('kk.json') as json_file:
    json_data = json_file.read()

    data = json.loads(json_data)
except Exception as e:
    print( e)

with open('bar.csv', 'at') as csv_file:
    writer = csv.writer(csv_file)#, quoting=csv.QUOTE_MINIMAL)
    for item in data:
        item_values = []
        for key in item:
            if write_header:
                item_keys.append(key)
            value = item.get(key, '')
            if (type(value)==t):
                item_values.append(value.encode('utf-8'))
            else:
                item_values.append(value)
        if write_header:
            writer.writerow(item_keys)
            write_header = False
        writer.writerow(item_values)