python对excel文件去重

import os
import pandas as pd
# 输入文件夹路径和输出文件夹路径
input_folder = ""
output_folder = ''
os.makedirs(output_folder, exist_ok=True)
for file_name in os.listdir(input_folder):
    if file_name.endswith('.xlsx'):
        input_file_path = os.path.join(input_folder, file_name)
        df = pd.read_excel(input_file_path)
        distinct_columns = ['table_hive_name', 'column_name'] #按指定字段去重
        if all(column in df.columns for column in distinct_columns):
            # df_unique = df.drop_duplicates()
            df_unique = df.drop_duplicates(subset=distinct_columns)
            output_file_path = os.path.join(output_folder, file_name)
            df_unique.to_excel(output_file_path, index=False)
        else:
            print(f"{file_name}不存在{distinct_columns}")