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

令人惊讶的是，我发现到目前为止贴在这里的答案都没有正确处理所有可能的场景(例如，嵌套字典，嵌套列表，无值等)。

这个解决方案应该适用于所有场景:

def flatten_json(json):
    def process_value(keys, value, flattened):
        if isinstance(value, dict):
            for key in value.keys():
                process_value(keys + [key], value[key], flattened)
        elif isinstance(value, list):
            for idx, v in enumerate(value):
                process_value(keys + [str(idx)], v, flattened)
        else:
            flattened['__'.join(keys)] = value

    flattened = {}
    for key in json.keys():
        process_value([key], json[key], flattened)
    return flattened

由于数据看起来是字典格式，因此似乎应该实际使用csv.DictWriter()来实际输出带有适当标题信息的行。这将使转换更容易处理。然后fieldnames参数将正确地设置顺序，而第一行的输出作为标题将允许稍后由csv.DictReader()读取和处理。

例如，Mike Repass使用

output = csv.writer(sys.stdout)

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

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

不过，只需将初始设置更改为 输出= csv。DictWriter数据(文件集,字段名= [0]. keys ())

注意，由于字典中元素的顺序没有定义，您可能必须显式地创建字段名条目。一旦你这样做了，writerow就可以工作了。然后写操作就像最初显示的那样工作。

Alec的回答很好，但在存在多层嵌套的情况下行不通。下面是一个支持多层嵌套的修改版本。如果嵌套对象已经指定了自己的键(例如Firebase Analytics / BigTable / BigQuery数据)，它也会使头名称更好一些:

"""Converts JSON with nested fields into a flattened CSV file.
"""

import sys
import json
import csv
import os

import jsonlines

from orderedset import OrderedSet

# from https://stackoverflow.com/a/28246154/473201
def flattenjson( b, prefix='', delim='/', val=None ):
  if val is None:
    val = {}

  if isinstance( b, dict ):
    for j in b.keys():
      flattenjson(b[j], prefix + delim + j, delim, val)
  elif isinstance( b, list ):
    get = b
    for j in range(len(get)):
      key = str(j)

      # If the nested data contains its own key, use that as the header instead.
      if isinstance( get[j], dict ):
        if 'key' in get[j]:
          key = get[j]['key']

      flattenjson(get[j], prefix + delim + key, delim, val)
  else:
    val[prefix] = b

  return val

def main(argv):
  if len(argv) < 2:
    raise Error('Please specify a JSON file to parse')

  print "Loading and Flattening..."
  filename = argv[1]
  allRows = []
  fieldnames = OrderedSet()
  with jsonlines.open(filename) as reader:
    for obj in reader:
      # print 'orig:\n'
      # print obj
      flattened = flattenjson(obj)
      #print 'keys: %s' % flattened.keys()
      # print 'flattened:\n'
      # print flattened
      fieldnames.update(flattened.keys())
      allRows.append(flattened)

  print "Exporting to CSV..."
  outfilename = filename + '.csv'
  count = 0
  with open(outfilename, 'w') as file:
    csvwriter = csv.DictWriter(file, fieldnames=fieldnames)
    csvwriter.writeheader()
    for obj in allRows:
      # print 'allRows:\n'
      # print obj
      csvwriter.writerow(obj)
      count += 1

  print "Wrote %d rows" % count



if __name__ == '__main__':
  main(sys.argv)

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!

这段代码应该适用于您，假设您的JSON数据在一个名为data. JSON的文件中。

import json
import csv

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

with open("data.csv", "w") as file:
    csv_file = csv.writer(file)
    for item in data:
        fields = list(item['fields'].values())
        csv_file.writerow([item['pk'], item['model']] + fields)