I have with me a script that converts jsonl files in a selected directory to csv files in another specified location. However, upon converting the files to csv format, the final created csv file contains a .jsonl extension before the .csv (Think file.jsonl.csv
) Any ideas on how to remove the .jsonl extension before adding the csv extension at the back? I hope I can be able to get rid of the .jsonl extension for the csv file as it may be confusing in future. Thank you!
Sample CSV file created:
20210531_CCXT_FTX_DOGEPERP.jsonl.csv
My script:
import glob
import json
import csv
import time
start = time.time()
#import pandas as pd
from flatten_json import flatten
#Path of jsonl file
File_path = (r'C:\Users\Natthanon\Documents\Coding 101\Python\JSONL')
#reading all jsonl files
files = [f for f in glob.glob( File_path + "**/*.jsonl", recursive=True)]
i = 0
for f in files:
with open(f, 'r') as F:
#creating csv files
with open(r'C:\Users\Natthanon\Documents\Coding 101\Python\CSV\\' + f.split("\\")[-1] + ".csv", 'w' , newline='') as csv_file:
thewriter = csv.writer(csv_file)
thewriter.writerow(["symbol", "timestamp", "datetime","high","low","bid","bidVolume","ask","askVolume","vwap","open","close","last","previousClose","change","percentage","average","baseVolume","quoteVolume"])
for line in F:
#flatten json files
data = json.loads(line)
data_1 = flatten(data)
#headers should be the Key values from json files that make Column header
thewriter.writerow([data_1['symbol'],data_1['timestamp'],data_1['datetime'],data_1['high'],data_1['low'],data_1['bid'],data_1['bidVolume'],data_1['ask'],data_1['askVolume'],data_1['vwap'],data_1['open'],data_1['close'],data_1['last'],data_1['previousClose'],data_1['change'],data_1['percentage'],data_1['average'],data_1['baseVolume'],data_1['quoteVolume']])