multi-sheet-reading-and-analysis

Step1 统计多工作表总行数，并根据数据量级（如≥1万行）动态启用Parquet格式转换以优化大文件读取性能。

import pandas as pd
import os
from openpyxl import load_workbook

file_path = "your_excel_file.xlsx"
xls = pd.ExcelFile(file_path)
sheet_names = xls.sheet_names

# 统计所有sheet的数据行数
total_rows = 0
for sheet in sheet_names:
    wb = load_workbook(file_path, read_only=True, data_only=True)
    ws = wb[sheet]
    max_row = ws.max_row
    data_rows = max_row - 1 if max_row > 0 else 0
    total_rows += data_rows
    wb.close()