Word 文档（Docx）合并、转 Html5 并内嵌 Base64 图片的 Python GUI 工具

#! /usr/bin/env python3
# -*- coding: utf-8 -*-
# 将 docx 转化为 html

import os
import base64
import shutil
import tkinter as tk
from tkinter import filedialog
from lxml import etree
from win32com import client as wc
from docx import Document
from docxcompose.composer import Composer

def merge_doc(docx_list: list, docx_tar: str, docx_list_src: str):
    """
    docx_list: word 文档名称列表，如 ["word1.docx", "word2.docx"]
    docx_tar: 合并后 word 文档的存储目标目录
    docx_list_src: 待合并 word 文档的源文件目录
    """
    if len(docx_list) == 0:
        return
    # 以第一个 word 文档作为合并基文档
    base_docx = os.path.join(docx_list_src, docx_list[0])
    tar_doc = Document(base_docx)
    tar_composer = Composer(tar_doc)
    # 依次追加后续文档
    for next_doc in docx_list[1:]:
        next_doc_path = os.path.join(docx_list_src, next_doc)
        tar_composer.append(Document(next_doc_path))
    # 保存合并后的文档
    docx_tar_file = os.path.join(docx_tar, "introduce.docx")
    tar_composer.save(docx_tar_file)

def convert_docx_html_pywin(docx_file_path: str) -> str:
    """
    docx_file_path: word 原文档路径
    """
    # 调用 Windows Word 的 COM 宏
    word = wc.Dispatch('Word.Application')
    doc = word.Documents.Open(docx_file_path)
    html_file_path = os.path.join(os.path.dirname(docx_file_path),
                                  os.path.basename(docx_file_path).split(".")[0] + ".html")
    # 另存为 Html（格式代码 10）
    doc.SaveAs(html_file_path, 10)
    doc.Close()
    word.Quit()

    # 编码转换：GBK → UTF-8
    fp = open(html_file_path, "rb")
    html_gb = fp.read()
    fp.close()
    fp = open(html_file_path, "wb")
    fp.write(html_gb.decode("gbk").replace("charset=gb2312", "charset=utf-8").encode("utf-8"))
    fp.close()
    return html_file_path

def convert_pic_base64(img_path: str) -> str:
    """
    img_path: 图片路径
    return: Base64 编码串
    """
    fp = open(img_path, "rb")
    img_content = fp.read()
    img_base64 = base64.b64encode(img_content)

    img_base64_str = str(img_base64, "utf-8")  # bytes 转 utf-8 字符串
    img_base64_tmp = f"data:image/{os.path.splitext(img_path)[-1][1:]};base64,{img_base64_str}"
    return img_base64_tmp

def process_html_img_tag(html_tar_file: str):
    """
    html_tar_file: word 转存 html 的原始文件路径
    """
    # 当前转化图片所在目录
    dir_path = os.path.dirname(html_tar_file)
    # 解析 html 并替换 img 标签的 src
    html_content = etree.parse(html_tar_file, etree.HTMLParser())
    tmp_files = []
    for img_tag in html_content.xpath("//img"):
        if img_tag.attrib["src"] == "":
            continue
        src_img_path = os.path.join(dir_path, img_tag.attrib["src"])
        tmp_files.append(os.path.dirname(src_img_path))
        src_img_b64code = convert_pic_base64(src_img_path)
        img_tag.attrib["src"] = src_img_b64code

    # 去除转换后 html 中的 system URL 和 public ID
    html_content.docinfo.system_url = None
    html_content.docinfo.public_id = None
    # 将 lxml 处理后的字节内容写入 utf-8 html 文件
    f = open(html_tar_file, "w", encoding="utf-8")
    # method=html 去除冗余信息
    f.write(etree.tostring(html_content, encoding="utf-8", method="html", pretty_print=True).decode("utf-8"))
    f.close()

    for p in tmp_files:
        shutil.rmtree(p)


# Word 转 Html 总成
def convert(docx_path: str):
    html_path = convert_docx_html_pywin(docx_path)
    process_html_img_tag(html_path)
    return html_path.replace("\\", "/")

window = tk.Tk()
window.title("Word转Html工具")
window.geometry('600x300')

# 输入框 1：源文件路径
path_var = tk.StringVar()
entry = tk.Entry(window, textvariable=path_var, width=60)
entry.place(x=20, y=10, anchor='nw')

# 输入框 2：转换结果路径
path_var1 = tk.StringVar()
entry1 = tk.Entry(window, textvariable=path_var1, width=60)
entry1.place(x=20, y=60, anchor='nw')


def choose_file_click():
    """选择文件事件"""
    file_types = [("word文件", "*.docx")]
    file_name = filedialog.askopenfilename(title='选择单个文件',
                                           filetypes=file_types,
                                           initialdir='./')
    path_var.set(file_name)


def convert_file_click():
    """Word 转 Html 事件"""
    src_file_path = path_var.get()
    convert_file_path = convert(src_file_path)
    path_var1.set(convert_file_path)


def clear_click():
    """清空所有输入"""
    path_var.set("")
    path_var1.set("")


choose_btn = tk.Button(window, text='选择', command=choose_file_click)
choose_btn.place(x=450, y=10, anchor='nw')
convert_btn = tk.Button(window, text='转化', command=convert_file_click)
convert_btn.place(x=450, y=60, anchor='nw')
clear_btn = tk.Button(window, text='清空', command=clear_click)
clear_btn.place(x=450, y=100, anchor='nw')

window.mainloop()

if __name__ == '__main__':
    docs = ["xx.docx", "yy.docx"]
    tar = r""
    src = r""
    merge_doc(docs, tar, src)

<p class="MsoNormal" style="text-align:justify;text-justify:inter-ideograph;line-height:normal">
    <span style='font-size:10.5pt;font-family:"Rounded Mplus 1c"'>
        <img width="601" height="159" id="image1.png" src="data:image/gif;base64,R0lGODlhWQKfAHcAMSH...+GcAQEAOw==">
    </span>
</p>