如何提取出文件夹中同种类型文件，并分类保存

import tkinter as tk from tkinter import filedialog from pathlib import Path from docx import Document from openpyxl import Workbook def get_colspan(cell): """安全获取列合并跨度""" try: return cell._tc.grid_span except AttributeError: return 1 def process_table(table): """精确解析表格结构""" # 计算实际最大列数 max_cols = 0 for row in table.rows: current_cols = 0 for cell in row.cells: current_cols += get_colspan(cell) max_cols = max(max_cols, current_cols) # 初始化网格 grid = [] for row in table.rows: current_row = [None] * max_cols col_cursor = 0 for cell in row.cells: # 跳过已填充列 while col_cursor < max_cols and current_row[col_cursor] is not None: col_cursor += 1 # 处理合并列 colspan = get_colspan(cell) text = cell.text.strip() or "" # 确保空字符串 # 填充单元格 for i in range(colspan): if col_cursor + i < max_cols: current_row[col_cursor + i] = text col_cursor += colspan grid.append(current_row) # 平铺数据并替换None为空字符串 return [cell if cell is not None else "" for row in grid for cell in row] def save_to_excel(data, output_path): """分页保存超大Excel文件""" MAX_COLUMNS = 16384 # Excel最大列限制 wb = Workbook() wb.remove(wb.active) # 删除默认工作表 # 拆分数据到多个工作表 for part_index in range(0, len(data), MAX_COLUMNS): part_data = data[part_index:part_index + MAX_COLUMNS] # 创建新工作表 ws = wb.create_sheet(title=f"Part{part_index//MAX_COLUMNS + 1}") # 写入数据到第一行 for col_idx, value in enumerate(part_data, 1): ws.cell(row=1, column=col_idx, value=value) wb.save(output_path) def process_docx_files(): root = tk.Tk() root.withdraw() # 选择文件夹 folder_path = filedialog.askdirectory(title="请选择包含docx文件的文件夹") if not folder_path: print("操作已取消") return # 处理文件 for docx_path in Path(folder_path).glob("*.docx"): try: doc = Document(docx_path) all_data = [] # 提取所有表格数据 for table in doc.tables: table_data = process_table(table) if table_data: all_data.extend(table_data) if not all_data: print(f"跳过无表格文件：{docx_path.name}") continue # 生成输出路径 output_path = docx_path.with_name(f"{docx_path.stem}_横向结果.xlsx") # 保存Excel文件 save_to_excel(all_data, output_path) print(f"成功保存：{output_path.name}") except Exception as e: print(f"处理失败：{docx_path.name} - {str(e)}") if __name__ == "__main__": process_docx_files() print("\n处理完成！") input("按回车键退出...")上述代码能成功运行生成xlsx文件，但仅处理了文件夹第一个docx文件，并且生成的xlsx文件中同一个值有9个单元格都是一样的重复值，还有大部分空白单元格，请将代码改进能够处理文件夹里的多个文件，仅生成的一个去重去空白单元格的xlsx文件。