Python读取多格式Excel并实现跨表匹配合并的完整示例

import pandas as pd
import xlrd
import openpyxl

def read_excel_any(path, sheet_name=None, skip_header_rows=0, skip_first_column=False):
    """
    支持 XLS/XLSX 的通用读取函数
    - skip_header_rows: 跳过前 N 行
    - skip_first_column: 是否跳过第一列（序号）
    """
    if path.lower().endswith(".xls"):
        book = xlrd.open_workbook(path)
        sheet = book.sheet_by_name(sheet_name) if sheet_name else book.sheet_by_index(0)

        data = []
        for r in range(sheet.nrows):
            if r < skip_header_rows:
                continue
            row = sheet.row_values(r)
            if skip_first_column:
                row = row[1:]
            data.append(row)

        df = pd.DataFrame(data[1:], columns=data[0])
        return df

    else:  # XLSX
        df = pd.read_excel(
            path,
            sheet_name=sheet_name,
            engine="openpyxl",
            skiprows=skip_header_rows
        )
        if skip_first_column:
            df = df.iloc[:, 1:]
        return df


# ===== 配置区（示例） ===== #
main_file = "主表.xls"
main_sheet = "数据表"

info_file = "信息表.xlsx"
info_sheet = "全部信息"

info_skip_header = 1
info_skip_first_col = True
# ======================== #

# 读取主表
df_main = read_excel_any(main_file, sheet_name=main_sheet)

# 读取信息表
df_info = read_excel_any(
    info_file,
    sheet_name=info_sheet,
    skip_header_rows=info_skip_header,
    skip_first_column=info_skip_first_col
)

# 确保两张表都有“姓名”列
if "姓名" not in df_main.columns or "姓名" not in df_info.columns:
    raise ValueError("两份表格必须都包含“姓名”列！")

# 设置信息表的索引
df_info_index = df_info.set_index("姓名")

# 按姓名匹配
matched_data = []
for name in df_main["姓名"]:
    if name in df_info_index.index:
        matched_data.append(df_info_index.loc[name].to_dict())
    else:
        # 不存在则填空
        matched_data.append({col: None for col in df_info.columns if col != "姓名"})

df_match = pd.DataFrame(matched_data)

# 匹配内容插入到指定位置（示例：插入到第 8 列之后）
insert_pos = 8
cols_main = df_main.columns.tolist()
new_cols = cols_main[:insert_pos + 1] + df_match.columns.tolist() + cols_main[insert_pos + 1:]

df_out = pd.concat([df_main, df_match], axis=1)[new_cols]

df_out.to_excel("输出结果.xlsx", index=False)

df_info.set_index("姓名")