fix option 9 duplicates

This commit is contained in:
root 2025-05-04 20:24:36 +02:00
parent 997617abe6
commit 7c3c820a3b

View file

@ -1122,7 +1122,9 @@ Maintenance:
try:
csvdf = pd.read_csv(csvfilepath)
print_colors(f"Removing duplicates in {csvfilepath}")
csvdf = csvdf.drop_duplicates(subset=['URL'])
#print_colors(f"{csvdf[['URL']]}")
csvdf = csvdf.drop_duplicates(subset=['URL'], keep="first", inplace=False)
#print_colors(f"{csvdf[['URL']]}")
csvdf.to_csv(csvfilepath, index=False)
print_colors(f"Cleaned data:\n{csvdf[['URL']]}")
except FileNotFoundError: