根据你的需求，这里提供一套完整的Python解决方案，支持递归遍历子文件夹、提取Word文档内容（段落+表格），并整合到Excel中。以下是代码实现及详细说明：
一个单元格一个word的全部内容
完整代码
# -*- coding: utf-8 -*-
import os
from docx import Document
import pandas as pd
from tqdm import tqdm # 需安装：pip install tqdmdef extract_word_content(doc_path):"""提取Word文档中的段落和表格内容"""try:doc = Document(doc_path)content = []# 提取段落文本for para in doc.paragraphs:if para.text.strip():content.append(('paragraph', para.text))# 提取表格内容（按行合并）for table in doc.tables:for row in table.rows:row_text = ' | '.join([cell.text.strip() for cell in row.cells])content.append(('table_row', row_text))return '\n'.join([f"[{type}] {text}" for type, text in content])except Exception as e:return f"Error reading file: {str(e)}"def process_folder(root_folder):"""遍历文件夹并提取所有Word文档"""data = []# 遍历所有子文件夹for root, _, files in os.walk(root_folder):# 筛选Word文件（兼容.doc和.docx）word_files = [f for f in files if f.lower().endswith(('.doc', '.docx'))]# 显示进度条（需安装tqdm）for file in tqdm(word_files, desc=f"Processing {os.path.basename(root)}"):file_path = os.path.join(root, file)content = extract_word_content(file_path)data.append({"文件名": file,"完整路径": file_path,"文件内容": content})return pd.DataFrame(data)if __name__ == "__main__":# 配置参数folder_path = r"C:\Users\esensoft\Desktop\报名推荐" # 修改为实际路径output_excel = "汇总结果.xlsx"# 执行处理df = process_folder(folder_path)# 导出Excel（自动处理格式）with pd.ExcelWriter(output_excel, engine='openpyxl') as writer:df.to_excel(writer, index=False, sheet_name='文档汇总')# 自动调整列宽for column in df.columns:max_len = max(df[column].astype(str).map(len).max(), len(column))writer.sheets['文档汇总'].column_dimensions[writer.sheets['文档汇总'].cell(row=
)
