From 7c3c820a3b117de88497028b2f1505ebfbf4d8f4 Mon Sep 17 00:00:00 2001 From: root Date: Sun, 4 May 2025 20:24:36 +0200 Subject: [PATCH] fix option 9 duplicates --- scripts/lantern.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index 65f1cde..81f8975 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -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: