ready to delete duplicated files

deal_duplicate_files.py

@@ -1,4 +1,5 @@
 import pathlib
+import os
 import argparse
 from numpy import source
 import pandas as pd
@@ -15,6 +16,11 @@ if __name__ == "__main__":
                         type=str,
                         help='csv file to the directory that be compared')
 
+    parser.add_argument('--remove',
+                        type=str,
+                        help='remove duplicated file or not',
+                        choices=['True','False'])
+
     args = parser.parse_args()
     csv_source = args.source
     csv_target = args.target
@@ -40,4 +46,7 @@ if __name__ == "__main__":
 
     for row in df_filtered.Path:
         p = pathlib.Path(row)
-        print(str(p) + ": " + str(p.exists()))
+        print(str(p) + ": " + str(p.exists()))
+        if args.remove == "True" and p.exists() == True:
+            os.remove(p)
+            print(str(p) + " Removed")

mv_unique_files.py

@@ -101,7 +101,7 @@ if __name__ == "__main__":
         
         if args.csv_path:
             csv_path = args.csv_path
-        df_csv.to_csv(csv_path)
+        df_csv.to_csv(csv_path,index_label='Index')
     else:
         for x in paths:
             print(str(x))