Created
June 22, 2022 08:12
-
-
Save slhck/3122d45b40494de05feef77b6e3e0808 to your computer and use it in GitHub Desktop.
Convert CSV to NDJSON (LDJSON)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
# | |
# csv_to_ndjson.py | |
# | |
# Author: Werner Robitza | |
# | |
# Convert CSV files to .ndjson. | |
# This assumes the same keys being used in every line of the input file. | |
# It works on a line-by-line basis, so it should be fast and memory-efficient. | |
import json | |
import argparse | |
import csv | |
from tqdm import tqdm | |
def convert_to_ndjson(csv_file, ndjson_file): | |
with open(csv_file, "r") as in_f: | |
with open(ndjson_file, "w") as out_f: | |
csv_reader = csv.DictReader(in_f) | |
for row in tqdm(csv_reader): | |
out_f.write(json.dumps(row) + "\n") | |
def main(): | |
parser = argparse.ArgumentParser( | |
formatter_class=argparse.ArgumentDefaultsHelpFormatter | |
) | |
parser.add_argument("input", help="input .csv") | |
parser.add_argument("output", help="output .ndjson") | |
cli_args = parser.parse_args() | |
convert_to_ndjson(cli_args.input, cli_args.output) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment