删除CSV文件的特定列中具有重复值的行

import csv

def remove_duplicate_rows(csv_file, column_index):
    data = []
    unique_values = set()

    with open(csv_file, 'r') as file:
        reader = csv.reader(file)
        headers = next(reader)
        
        for row in reader:
            value = row[column_index]
            
            if value in unique_values:
                continue
            
            unique_values.add(value)
            data.append(row)

    with open(csv_file, 'w', newline='') as file:
        writer = csv.writer(file)
        writer.writerow(headers)
        writer.writerows(data)

# 使用示例
csv_file = 'data.csv'  # CSV文件路径
column_index = 2  # 需要检查重复值的列索引，假设为第三列

remove_duplicate_rows(csv_file, column_index)