用 python 将多个Word Doc文档，生成epub格式电

python 生成从指定目录读取doc文档，
按每个doc作为一个章节生成epub文件
每个文档名称为目录名称

依赖(pip install -r requirments.txt):

docx
ebooklib
natsort

实现如下：

import os
import uuid

import docx
from ebooklib import epub

# Define the path to the directory containing the DOC files
from natsort import natsorted

doc_dir = "D:\\Download\\文稿集"

# Create a new EPUB book
book = epub.EpubBook()

# Set the book's metadata
book.set_identifier(str(uuid.uuid4()))
book.set_title(os.path.basename(doc_dir))
book.set_language("zh")


def docx2html(doc):
    html = []
    for p in doc.paragraphs:
        html.append(f"<p>{p.text}</p>")
    return "\n".join(html)

toc = []
# Iterate over the DOC files in the directory

files = os.listdir(doc_dir)
sorted_files = natsorted(files)

for filename in sorted_files:


    if filename.endswith(".doc") or filename.endswith(".docx"):
        # Open the DOC file using python-docx
        doc = docx.Document(os.path.join(doc_dir, filename))

        chapterName= filename[0:filename.rindex(".")]
        # Create a new EPUB chapter for the DOC file
        chapter = epub.EpubHtml(title=chapterName, file_name="chapter_{}.xhtml".format(filename))
        chapter.content = docx2html(doc)

        # Add the chapter to the book
        book.add_item(chapter)
        book.spine.append(chapter)
        # Add an entry to the Table of Contents
        toc.append(epub.Link("chapter_{}.xhtml".format(filename), chapterName, filename))

book.toc = tuple(toc)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())

epub_path = f'{doc_dir}\\{book.title}.epub'
epub.write_epub(epub_path, book, {})