from pathlib import Path
import time
import parser
import argparse
import pandas as pd
import os
import warnings

warnings.filterwarnings("ignore")

parser = argparse.ArgumentParser(description="Process some integers.")

parser.add_argument("path", help="define the directory to folder/file")
parser.add_argument("--verbose", help="display processing information")

start = time.time()


def main(path_xlsx, verbose):
    if (".xlsx" in str(path_xlsx).lower()) and path_xlsx.is_file():
        xlsx_files = [Path(path_xlsx)]
    else:
        xlsx_files = list(Path(path_xlsx).glob("*.xlsx"))    
 

    df = pd.DataFrame()
    for fn in xlsx_files:
        all_dfs = pd.read_excel(fn, sheet_name=None)
        for sheet_name, df in all_dfs.items():
            df = df.assign(DataSource=Path(fn.name))
            x=os.path.splitext(fn.name)[0]
            path=r'Output'
            df.to_csv(os.path.join(path,f'{sheet_name}+{x}.csv'),index=False)            
        
if __name__ == "__main__":
    start = time.time()
    args = parser.parse_args()
    path = Path(args.path)
    verbose = args.verbose
    main(path, verbose)  #Calling Main Function
    print("Processed time:", time.time() - start)  #Total Time
        

(Apr-08-2021, 07:40 AM)buran Wrote: You specifically filter only xlsx files. Change your code to process also xls file.
Note for xls files you will need to instal xlrd package in addition to openpyxl.
https://pandas.pydata.org/docs/reference/api/pandas.read_excel.html#pandas.read_excel