Python实现Excel多表自动VLOOKUP关联匹配

pip install pandas openpyxl

import pandas as pd

def auto_vlookup(main_file, lookup_file, main_key, lookup_key, lookup_columns, output_file="关联结果.xlsx", how='left'):
    """
    Python 版 VLOOKUP 自动关联两个 Excel 表

    参数:
        main_file: 主表文件路径（保留此表的全部数据）
        lookup_file: 被查找的表文件路径
        main_key: 主表中用于匹配的列名
        lookup_key: 查找表中用于匹配的列名
        lookup_columns: 需要从查找表中提取的列名列表，如 ['评分', '等级']
        output_file: 输出文件名
        how: 关联方式，'left'/'inner'/'right'/'outer'
    """
    # 1. 读取两个表
    main_df = pd.read_excel(main_file, engine='openpyxl')
    lookup_df = pd.read_excel(lookup_file, engine='openpyxl')

    print(f"主表: {len(main_df)} 行 × {len(main_df.columns)} 列")
    print(f"查找表: {len(lookup_df)} 行 × {len(lookup_df.columns)} 列")

    # 2. 验证列名是否存在
    for col in [main_key, lookup_key] + lookup_columns:
        if col not in main_df.columns and col not in lookup_df.columns:
            print(f"错误: 列 '{col}' 在两个表中都不存在！")
            return

    # 3. 从查找表中只保留需要的列
    select_columns = [lookup_key] + lookup_columns
    lookup_subset = lookup_df[select_columns]

    # 4. 执行关联（一行代码完成 VLOOKUP！）
    result = pd.merge(
        main_df,
        lookup_subset,
        left_on=main_key,
        right_on=lookup_key,
        how=how
    )

    # 5. 如果关联列名不同，删除重复的查找列
    if main_key != lookup_key:
        result.drop(columns=[lookup_key], inplace=True)

    # 6. 统计匹配情况
    matched = result[lookup_columns[0]].notna().sum()
    unmatched = len(result) - matched
    print(f"\n匹配结果: {matched} 行匹配成功, {unmatched} 行未匹配")

    # 7. 导出结果
    result.to_excel(output_file, index=False, engine='openpyxl')
    print(f"结果已保存: {output_file} ({len(result)} 行)")

    return result


# ==================== 多表关联 ====================
def multi_table_vlookup(base_file, lookup_files, key_column, output_file="多表关联结果.xlsx"):
    """
    一个主表关联多个查找表

    参数:
        base_file: 主表路径
        lookup_files: 列表，每个元素为 {'file': '文件路径', 'key': '匹配列', 'columns': ['需要提取的列']}
        key_column: 主表的匹配列名
        output_file: 输出文件
    """
    result = pd.read_excel(base_file, engine='openpyxl')
    print(f"主表: {len(result)} 行")

    for lookup_info in lookup_files:
        lookup_df = pd.read_excel(lookup_info['file'], engine='openpyxl')

        select_cols = [lookup_info['key']] + lookup_info['columns']
        lookup_subset = lookup_df[[c for c in select_cols if c in lookup_df.columns]]

        result = pd.merge(
            result,
            lookup_subset,
            left_on=key_column,
            right_on=lookup_info['key'],
            how='left'
        )

        if key_column != lookup_info['key']:
            result.drop(columns=[lookup_info['key']], inplace=True)

        print(f"已关联 {lookup_info['file']}")

    result.to_excel(output_file, index=False, engine='openpyxl')
    print(f"\n多表关联完成: {output_file}")


# ==================== 使用示例 ====================
if __name__ == "__main__":
    # ========== 示例 1：关联员工绩效 ==========
    auto_vlookup(
        main_file="员工信息表.xlsx",
        lookup_file="绩效考核表.xlsx",
        main_key="工号",
        lookup_key="工号",
        lookup_columns=["评分", "等级"],
        output_file="员工完整信息表.xlsx",
        how='left'  # 保留所有员工，没有绩效的显示 NaN
    )

    # ========== 示例 2：多表关联 ==========
    # multi_table_vlookup(
    #     base_file="员工信息表.xlsx",
    #     lookup_files=[
    #         {'file': '绩效考核表.xlsx', 'key': '工号', 'columns': ['评分', '等级']},
    #         {'file': '薪资表.xlsx', 'key': '工号', 'columns': ['基本工资', '绩效奖']},
    #         {'file': '培训记录表.xlsx', 'key': '工号', 'columns': ['培训课程', '学时']},
    #     ],
    #     key_column="工号",
    #     output_file="员工全景档案表.xlsx"
    # )

result = pd.merge(main_df, lookup_subset, left_on=main_key, right_on=lookup_key, how='left')

=VLOOKUP(A2, 查找表!A:C, 2, FALSE)

select_columns = [lookup_key] + lookup_columns
lookup_subset = lookup_df[select_columns]

matched = result[lookup_columns[0]].notna().sum()
unmatched = len(result) - matched

# 统一为字符串并补零
main_df['工号'] = main_df['工号'].astype(str).str.zfill(3)
lookup_df['工号'] = lookup_df['工号'].astype(str).str.zfill(3)

result = pd.merge(
    main_df, lookup_df,
    left_on=['姓名', '部门'],
    right_on=['姓名', '部门'],
    how='left'
)

# 查找表去重（保留第一条）
lookup_df.drop_duplicates(subset=['工号'], keep='first', inplace=True)

# 检查是否有重复
print(lookup_df['工号'].duplicated().sum())

# 去重后再关联
lookup_df = lookup_df.drop_duplicates(subset=['工号'], keep='first')

# 统一转为字符串
main_df['工号'] = main_df['工号'].astype(str)
lookup_df['工号'] = lookup_df['工号'].astype(str)