How can I convert JSON to CSV?

Use json_normalize from pandas:

• Using the sample data from the OP in a file named test.json.
• encoding='utf-8' has been used here, but may not be necessary for other cases.
• The following code takes advantage of the pathlib library.
  • .open is a method of pathlib.
  • Works with non-Windows paths too.
• Use pandas.to_csv(...) to save the data to a csv file.

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 Output:

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

Resources for more heavily nested JSON objects:

• SO Answers:
  • Flatten a JSON array with python
  • How to flatten nested JSON recursively, with flatten_json?
  • How to json_normalize a column with NaNs
  • Split / Explode a column of dictionaries into separate columns with pandas
  • See the json_normalize tag for other related questions.

Alec's answer is great, but it doesn't work in the case where there are multiple levels of nesting. Here's a modified version that supports multiple levels of nesting. It also makes the header names a bit nicer if the nested object already specifies its own key (e.g. Firebase Analytics / BigTable / BigQuery data):

"""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)

It is not a very smart way to do it, but I have had the same problem and this worked for me:

import csv

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

new_data = []

for i in data:
   flat = {}
   names = i.keys()
   for n in names:
      try:
         if len(i[n].keys()) > 0:
            for ii in i[n].keys():
               flat[n+"_"+ii] = i[n][ii]
      except:
         flat[n] = i[n]
   new_data.append(flat)  

f = open(filename, "r")
writer = csv.DictWriter(f, new_data[0].keys())
writer.writeheader()
for row in new_data:
   writer.writerow(row)
f.close()

Surprisingly, I found that none of the answers posted here so far correctly deal with all possible scenarios (e.g., nested dicts, nested lists, None values, etc).

This solution should work across all scenarios:

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

This code works for any given json file

# -*- 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()

This is a modification of @MikeRepass's answer. This version writes the CSV to a file, and works for both Python 2 and 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)

Try this

import csv, json, sys

input = open(sys.argv[1])
data = json.load(input)
input.close()

output = csv.writer(sys.stdout)

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

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

If we consider the below example for converting the json format file to csv formatted file.

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

The below code will convert the json file ( data3.json ) to csv file ( 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')])

The above mentioned code has been executed in the locally installed pycharm and it has successfully converted the json file to the csv file. Hope this help to convert the files.

Unfortunately I have not enouthg reputation to make a small contribution to the amazing @Alec McGail answer. I was using Python3 and I have needed to convert the map to a list following the @Alexis R comment.

Additionaly I have found the csv writer was adding a extra CR to the file (I have a empty line for each line with data inside the csv file). The solution was very easy following the @Jason R. Coombs answer to this thread: CSV in Python adding an extra carriage return

You need to simply add the lineterminator='\n' parameter to the csv.writer. It will be: csv_w = csv.writer( out_file, lineterminator='\n' )

You can use this code to convert a json file to csv file After reading the file, I am converting the object to pandas dataframe and then saving this to a CSV file

import os
import pandas as pd
import json
import numpy as np

data = []
os.chdir('D:\\Your_directory\\folder')
with open('file_name.json', encoding="utf8") as data_file:    
     for line in data_file:
        data.append(json.loads(line))

dataframe = pd.DataFrame(data)        
## Saving the dataframe to a csv file
dataframe.to_csv("filename.csv", encoding='utf-8',index= False)

I have tried a lot of the suggested solution (also Panda was not correctly normalizing my JSON) but the real good one which is parsing correctly the JSON data is from Max Berman.

I wrote an improvement to avoid new columns for each row and puts it to the existing column during parsing. It has also the effect to store a value as a string if only one data exists, and make a list if there are more values for that columns.

It takes an input.json file for input and spits out an output.csv.

import json
import pandas as pd

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, v, flattened)
                # process_value(keys + [str(idx)], v, flattened)
        else:
            key1 = '__'.join(keys)
            if not flattened.get(key1) is None:
                if isinstance(flattened[key1], list):
                    flattened[key1] = flattened[key1] + [value]
                else:
                    flattened[key1] = [flattened[key1]] + [value]
            else:
                flattened[key1] = value

    flattened = {}
    for key in json.keys():
        k = key
        # print("Key: " + k)
        process_value([key], json[key], flattened)
    return flattened

try:
    f = open("input.json", "r")
except:
    pass
y = json.loads(f.read())
flat = flatten_json(y)
text = json.dumps(flat)
df = pd.read_json(text)
df.to_csv('output.csv', index=False, encoding='utf-8')

I might be late to the party, but I think, I have dealt with the similar problem. I had a json file which looked like this

I only wanted to extract few keys/values from these json file. So, I wrote the following code to extract the same.

    """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()

I hope this will help. For details on how this code work you can check here