python批量将word文档提取到excel表格

矢岛舞美

某天工作中需要将大量word文档中的内容提取到excel表格里面来进行处理，所以便有了这个东西。

[Python] 纯文本查看 复制代码

import os
from docx import Document
import openpyxl
from tkinter import Tk, filedialog


def extract_text_from_docx(docx_path):
    doc = Document(docx_path)
    paragraphs = doc.paragraphs
    title = paragraphs[0].text if paragraphs else ''
    content = ''.join([f'<p>{p.text}</p>' for p in paragraphs[1:]])
    return title, content


def create_excel(excel_path):
    wb = openpyxl.Workbook()
    ws = wb.active
    ws.append(["标题", "内容"])
    wb.save(excel_path)
    return excel_path


def append_to_excel(data, excel_path):
    wb = openpyxl.load_workbook(excel_path)
    ws = wb.active

    for title, content in data:
        ws.append([title, content])

    wb.save(excel_path)


def main():
    # 使用Tkinter打开文件夹选择对话框
    root = Tk()
    root.withdraw()  # 隐藏主窗口
    folder_path = filedialog.askdirectory(title="选择包含Word文档的文件夹")

    if not folder_path:
        print("未选择文件夹，程序退出。")
        return

    excel_path = filedialog.asksaveasfilename(defaultextension=".xlsx", filetypes=[("Excel files", "*.xlsx")],
                                              title="保存Excel文件")

    if not excel_path:
        print("未选择保存路径，程序退出。")
        return

    # 创建Excel文件
    create_excel(excel_path)

    # 使用os.walk递归遍历文件夹
    for root_dir, _, files in os.walk(folder_path):
        data = []
        for filename in files:
            if filename.endswith(".docx"):
                docx_path = os.path.join(root_dir, filename)
                title, content = extract_text_from_docx(docx_path)
                data.append((title, content))

        # 将数据追加到Excel文件
        append_to_excel(data, excel_path)

    print(f"数据已成功保存到 {excel_path}")


if __name__ == "__main__":
    main()

优化版本，解决提取后内容有标签的问题

[Python] 纯文本查看 复制代码

import os
from docx import Document
import openpyxl
from tkinter import Tk, filedialog

def extract_text_from_docx(docx_path):
    doc = Document(docx_path)
    paragraphs = doc.paragraphs
    title = paragraphs[0].text if paragraphs else ''
    content = '\n'.join([p.text for p in paragraphs[1:]])
    return title, content

def create_excel(excel_path):
    wb = openpyxl.Workbook()
    ws = wb.active
    ws.append(["标题", "内容"])
    wb.save(excel_path)

def append_to_excel(data, excel_path):
    wb = openpyxl.load_workbook(excel_path)
    ws = wb.active

    for title, content in data:
        ws.append([title, content])

    wb.save(excel_path)

def main():
    # 使用Tkinter打开文件夹选择对话框
    root = Tk()
    root.withdraw()  # 隐藏主窗口
    folder_path = filedialog.askdirectory(title="选择包含Word文档的文件夹")

    if not folder_path:
        print("未选择文件夹，程序退出。")
        return

    excel_path = filedialog.asksaveasfilename(defaultextension=".xlsx", filetypes=[("Excel files", "*.xlsx")],
                                              title="保存Excel文件")

    if not excel_path:
        print("未选择保存路径，程序退出。")
        return

    # 创建Excel文件
    create_excel(excel_path)

    # 使用os.walk递归遍历文件夹
    for root_dir, _, files in os.walk(folder_path):
        data = []
        for filename in files:
            if filename.endswith(".docx"):
                docx_path = os.path.join(root_dir, filename)
                title, content = extract_text_from_docx(docx_path)
                data.append((title, content))

        # 将数据追加到Excel文件
        append_to_excel(data, excel_path)

    print(f"数据已成功保存到 {excel_path}")

if __name__ == "__main__":
    main()

Flanders

试了下 转换出来是这个效果，楼主能科普下doc内的内容格式改怎么写吗 这是我测试的文档 该如何正确修改 请教一下 doc_excel.zip (14.46 KB, 下载次数: 8)

2024-11-1 16:58 上传

点击文件名下载附件

Flanders

另外有没有大神有示例可以把 xlsx的数据“标题、内容、结论”批量提取到word文档保存吗

jalonewy

特定需求

gumu880310

感谢楼主，留个脚印。

wusim

请问有没已编译的程序

greatzdl

学习了 很小巧实用

hkkuup

在哪里？怎么用？？

cku

表格也可以搬过去吗

zhaoysh1004

感谢分享，每天一个编程小技巧

flylujun

WORD中的表格，文本，图片都可以搬过去吗