当前位置：首页 > news >正文

Python将Word转换为Excel

news 2025/7/31 18:27:44

现有大量的Word文档，每个文档中有大量的表格，需要将其转换为Excel。

Python处理源码

# 需要安装pip install xlsxwriter
import pandas as pd
from docx import Document
from pathlib import Path
from datetime import datetimedef process_docx(filepath):# 处理Word文档的主函数doc = Document(filepath)# 示例处理逻辑：提取所有段落文本content = [p.text for p in doc.paragraphs if p.text.strip()]print(f"成功处理文档: {filepath}")data = []monitor_time = ""# 提取监测时间for paragraph in doc.paragraphs:# print(paragraph.text)if "第12次：" in paragraph.text:monitor_time = parse_monitor_time(paragraph.text)print(f"提取监测时间: {monitor_time}")break# 处理所有表格index = 0for table in doc.tables:# 检查是否为数据表格（包含房屋编号列）if len(table.columns) >= 7 and "成果表" in table.cell(0,0).text:# print(table.cell(0,0).text)for row in table.rows[2:]:  # 跳过标题行first_cell_text = row.cells[0].text.strip()  # 获取第一个单元格的文本并去除首尾空格if "备注" in first_cell_text:  # 如果第一个单元格包含"备注"continue  # 跳过该行cells = [cell.text.replace("\n", "").replace("\r", "").strip() for cell in row.cells]if len(cells) >= 7:  # 确保数据完整# 构建输出记录record = {'点号': f"{cells[0].replace(" ", "")}-{cells[1]}",'初始值': cells[2],'检测值': cells[3],'累计值': cells[4],'监测时间': monitor_time,'上次监测时间': "2025/6/17 03:00"  # 根据备注补充}# print(record)data.append(record)return datadef generate_excel(data, output_path):# 生成标准格式Exceldf = pd.DataFrame(data) # 补充固定字段df['备注'] = '无'# 字段顺序调整columns_order = [ '点号', '初始值', '检测值', '累计值', '监测时间', '上次监测时间', '备注' ]df = df.reindex(columns=columns_order)# 填充空值df['上次监测时间'] = '2025-06-01'# 保存Excel# df.to_excel(output_path, index=False)with pd.ExcelWriter(output_path, engine='xlsxwriter') as writer:df.to_excel(writer, index=False, sheet_name='Sheet1')  # 导出数据worksheet = writer.sheets['Sheet1']# 手动设置列宽（单位：字符宽度）worksheet.set_column('A:A', 38)  # 设置A列为15字符宽度worksheet.set_column('B:B', 12)  # 设置B列为10字符宽度print(f"Excel文件已生成: {output_path}")print(f"Excel开始生成")
filepath=r"C:\Users\admin\Desktop\test.docx"
output_path=r"C:\Users\admin\Desktop\test.xlsx"
data = process_docx(filepath)
generate_excel(data, output_path)
print(f"Excel生成结束")