How to convert CSV file to multiline JSON?

Add the indent parameter to json.dumps

 data = {'this': ['has', 'some', 'things'],
         'in': {'it': 'with', 'some': 'more'}}
 print(json.dumps(data, indent=4))

Also note that, you can simply use json.dump with the open jsonfile:

json.dump(data, jsonfile)

import csv
import json
csvfile = csv.DictReader('filename.csv', 'r'))
output =[]
for each in csvfile:
    row ={}
    row['FirstName'] = each['FirstName']
    row['LastName']  = each['LastName']
    row['IDNumber']  = each ['IDNumber']
    row['Message']   = each['Message']
    output.append(row)
json.dump(output,open('filename.json','w'),indent=4,sort_keys=False)

As slight improvement to @MONTYHS answer, iterating through a tup of fieldnames:

import csv
import json

csvfilename = 'filename.csv'
jsonfilename = csvfilename.split('.')[0] + '.json'
csvfile = open(csvfilename, 'r')
jsonfile = open(jsonfilename, 'w')
reader = csv.DictReader(csvfile)

fieldnames = ('FirstName', 'LastName', 'IDNumber', 'Message')

output = []

for each in reader:
  row = {}
  for field in fieldnames:
    row[field] = each[field]
output.append(row)

json.dump(output, jsonfile, indent=2, sort_keys=True)

You can try this

import csvmapper

# how does the object look
mapper = csvmapper.DictMapper([ 
  [ 
     { 'name' : 'FirstName'},
     { 'name' : 'LastName' },
     { 'name' : 'IDNumber', 'type':'int' },
     { 'name' : 'Messages' }
  ]
 ])

# parser instance
parser = csvmapper.CSVParser('sample.csv', mapper)
# conversion service
converter = csvmapper.JSONConverter(parser)

print converter.doConvert(pretty=True)

Edit:

Simpler approach

import csvmapper

fields = ('FirstName', 'LastName', 'IDNumber', 'Messages')
parser = CSVParser('sample.csv', csvmapper.FieldMapper(fields))

converter = csvmapper.JSONConverter(parser)

print converter.doConvert(pretty=True)

I took @SingleNegationElimination’s response and simplified it into a three-liner that can be used in a pipeline:

import csv
import json
import sys

for row in csv.DictReader(sys.stdin):
    json.dump(row, sys.stdout)
    sys.stdout.write('n')

How about using Pandas to read the csv file into a DataFrame (pd.read_csv), then manipulating the columns if you want (dropping them or updating values) and finally converting the DataFrame back to JSON (pd.DataFrame.to_json).

Note: I haven’t checked how efficient this will be but this is definitely one of the easiest ways to manipulate and convert a large csv to json.

I see this is old but I needed the code from SingleNegationElimination however I had issue with the data containing non utf-8 characters. These appeared in fields I was not overly concerned with so I chose to ignore them. However that took some effort. I am new to python so with some trial and error I got it to work. The code is a copy of SingleNegationElimination with the extra handling of utf-8. I tried to do it with https://docs.python.org/2.7/library/csv.html but in the end gave up. The below code worked.

import csv, json

csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')

fieldnames = ("Scope","Comment","OOS Code","In RMF","Code","Status","Name","Sub Code","CAT","LOB","Description","Owner","Manager","Platform Owner")
reader = csv.DictReader(csvfile , fieldnames)

code = ''
for row in reader:
    try:
        print('+' + row['Code'])
        for key in row:
            row[key] = row[key].decode('utf-8', 'ignore').encode('utf-8')      
        json.dump(row, jsonfile)
        jsonfile.write('n')
    except:
        print('-' + row['Code'])
        raise

You can use Pandas DataFrame to achieve this, with the following Example:

import pandas as pd
csv_file = pd.DataFrame(pd.read_csv("path/to/file.csv", sep = ",", header = 0, index_col = False))
csv_file.to_json("/path/to/new/file.json", orient = "records", date_format = "epoch", double_precision = 10, force_ascii = True, date_unit = "ms", default_handler = None)

import csv
import json

file = 'csv_file_name.csv'
json_file = 'output_file_name.json'

#Read CSV File
def read_CSV(file, json_file):
    csv_rows = []
    with open(file) as csvfile:
        reader = csv.DictReader(csvfile)
        field = reader.fieldnames
        for row in reader:
            csv_rows.extend([{field[i]:row[field[i]] for i in range(len(field))}])
        convert_write_json(csv_rows, json_file)

#Convert csv data into json
def convert_write_json(data, json_file):
    with open(json_file, "w") as f:
        f.write(json.dumps(data, sort_keys=False, indent=4, separators=(',', ': '))) #for pretty
        f.write(json.dumps(data))


read_CSV(file,json_file)

Documentation of json.dumps()

def read():
    noOfElem = 200  # no of data you want to import
    csv_file_name = "hashtag_donaldtrump.csv"  # csv file name
    json_file_name = "hashtag_donaldtrump.json"  # json file name

    with open(csv_file_name, mode='r') as csv_file:
        csv_reader = csv.DictReader(csv_file)
        with open(json_file_name, 'w') as json_file:
            i = 0
            json_file.write("[")
            
            for row in csv_reader:
                i = i + 1
                if i == noOfElem:
                    json_file.write("]")
                    return

                json_file.write(json.dumps(row))

                if i != noOfElem - 1:
                    json_file.write(",")

Change the above three parameter, everything will be done.

Use pandas and the json library:

import pandas as pd
import json
filepath = "inputfile.csv"
output_path = "outputfile.json"

df = pd.read_csv(filepath)

# Create a multiline json
json_list = json.loads(df.to_json(orient = "records"))

with open(output_path, 'w') as f:
    for item in json_list:
        f.write("%sn" % item)