I have a JSON file I want to convert to a CSV file. How can I do this with Python?
I tried:
import json
import c
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)