基于键列使用python合并文本文件中的重复行

import csv

def merge_files(file1, file2, key_column):
    # 读取第一个文件并创建一个字典来存储数据
    data_dict = {}
    with open(file1, 'r') as f1:
        reader = csv.reader(f1)
        next(reader)  # 跳过标题行
        for row in reader:
            key = row[key_column]
            if key not in data_dict:
                data_dict[key] = row
            else:
                # 如果键已存在，则合并数据（这里简单地将新行追加到现有行后面）
                data_dict[key].extend(row)

    # 读取第二个文件并更新字典
    with open(file2, 'r') as f2:
        reader = csv.reader(f2)
        next(reader)  # 跳过标题行
        for row in reader:
            key = row[key_column]
            if key in data_dict:
                data_dict[key].extend(row)
            else:
                data_dict[key] = row

    # 将合并后的数据写入新文件
    with open('merged_file.csv', 'w', newline='') as outfile:
        writer = csv.writer(outfile)
        writer.writerow(next(reader))  # 写入标题行
        for key in data_dict:
            writer.writerow(data_dict[key])

# 使用示例
merge_files('file1.csv', 'file2.csv', 0)  # 假设键列是第一列（索引为0）