gbifocc-datasette / tab2csv.py
Nicky Nicolson
skip bad lines
e57384a
raw
history blame
457 Bytes
import argparse
import pandas as pd
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("inputfile")
parser.add_argument("outputfile")
args = parser.parse_args()
df = pd.read_csv(args.inputfile,
encoding='utf8',
keep_default_na=False,
on_bad_lines='skip',
sep='\t')
df.to_csv(outputfile, index=False, sep=',')