Python文档格式转换之Word转为EPUB的示例代码

pip install Spire.Doc

from spire.doc import *
from spire.doc.common import *

# 创建文档对象
doc = Document()

# 加载 Word 文件
doc.LoadFromFile("input.docx")

# 保存为 EPUB
doc.SaveToFile("output.epub", FileFormat.EPub)

# 释放资源
doc.Close()

doc = Document()
doc.LoadFromFile("input.docx")

# 创建图片对象并加载封面文件
picture = DocPicture(doc)
picture.LoadImage("cover.png")

# 保存时传入封面参数
doc.SaveToEpub("output_with_cover.epub", picture)

doc.Close()

import os

input_dir = "word_files/"
output_dir = "epub_files/"
os.makedirs(output_dir, exist_ok=True)

for filename in os.listdir(input_dir):
    if filename.endswith(".docx") or filename.endswith(".doc"):
        doc = Document()
        doc.LoadFromFile(os.path.join(input_dir, filename))
        
        epub_name = os.path.splitext(filename)[0] + ".epub"
        doc.SaveToFile(os.path.join(output_dir, epub_name), FileFormat.EPub)
        
        doc.Close()

pip install pypandoc

import pypandoc

def docx_to_epub_pandoc(input_path, output_path, title=None, author=None):
    """
    使用 Pandoc 将 DOCX 转换为 EPUB。
    """
    extra_args = [
        '--toc',                    # 生成目录
        '--toc-depth=2',            # 目录深度到二级标题
        '--metadata', f'title={title or "Untitled"}',
        '--metadata', f'author={author or "Unknown"}',
        '--standalone',
    ]

    pypandoc.convert_file(
        input_path,
        'epub',
        outputfile=output_path,
        extra_args=extra_args
    )
    print(f'✅ EPUB 已生成：{output_path}')

docx_to_epub_pandoc(
    'input.docx',
    'output.epub',
    title='我的电子书',
    author='作者名'
)

def docx_to_epub_pandoc_advanced(input_path, output_path, css_path=None, cover_path=None):
    extra_args = [
        '--toc',
        '--toc-depth=3',
        '--metadata', 'title=Advanced Book',
        '--metadata', 'author=Author Name',
    ]

    if css_path:
        extra_args.extend(['--css', css_path])

    if cover_path:
        extra_args.extend(['--epub-cover-image', cover_path])

    pypandoc.convert_file(
        input_path,
        'epub',
        outputfile=output_path,
        extra_args=extra_args
    )

import aspose.words as aw

def docx_to_epub_aspose(input_path, output_path):
    # 加载许可证（如有）
    license = aw.License()
    # license.set_license("license.lic")  # 取消注释并填入许可证路径

    doc = aw.Document(input_path)

    # 按分页符拆分章节
    options = aw.saving.HtmlSaveOptions()
    options.document_split_criteria = aw.saving.DocumentSplitCriteria.PAGE_BREAK
    options.save_format = aw.SaveFormat.EPUB

    doc.save(output_path, options)
    print(f'✅ EPUB 已生成：{output_path}')

from spire.doc import Document, FileFormat

def docx_to_epub_spire(input_path, output_path, cover_image=None):
    doc = Document()
    doc.LoadFromFile(input_path)

    if cover_image:
        from spire.doc import DocPicture
        picture = DocPicture(doc)
        picture.LoadImage(cover_image)
        doc.SaveToEpub(output_path, picture)
    else:
        doc.SaveToFile(output_path, FileFormat.EPub)

    doc.Close()
    print(f'✅ EPUB 已生成：{output_path}')

pip install python-docx ebooklib beautifulsoup4

import os
from docx import Document
from docx.enum.text import WD_ALIGN_PARAGRAPH
from ebooklib import epub
from bs4 import BeautifulSoup

def docx_paragraph_to_html(paragraph):
    """将 python-docx 的段落转换为 HTML。"""
    html_parts = []
    for run in paragraph.runs:
        text = run.text
        if not text:
            continue
        # 转义 HTML 特殊字符
        text = text.replace('&', '&').replace('<', '<').replace('>', '>')

        if run.bold:
            text = f'<strong>{text}</strong>'
        if run.italic:
            text = f'<em>{text}</em>'
        if run.underline:
            text = f'<u>{text}</u>'

        html_parts.append(text)

    content = ''.join(html_parts)
    if not content.strip():
        return ''

    # 根据 Word 样式映射为 HTML 标签
    style_name = paragraph.style.name if paragraph.style else ''

    if style_name.startswith('Heading 1'):
        return f'<h1>{content}</h1>'
    elif style_name.startswith('Heading 2'):
        return f'<h2>{content}</h2>'
    elif style_name.startswith('Heading 3'):
        return f'<h3>{content}</h3>'
    elif style_name.startswith('List'):
        return f'<li>{content}</li>'
    else:
        return f'<p>{content}</p>'


def docx_to_epub_pure(docx_path, epub_path, book_title=None, author=None):
    """纯 Python 实现：python-docx + ebooklib。"""
    doc = Document(docx_path)

    # 1. 将 Word 段落转换为 HTML 片段
    html_fragments = []
    in_list = False

    for para in doc.paragraphs:
        frag = docx_paragraph_to_html(para)
        if not frag:
            continue

        # 列表项包裹
        if frag.startswith('<li>'):
            if not in_list:
                html_fragments.append('<ul>')
                in_list = True
            html_fragments.append(frag)
        else:
            if in_list:
                html_fragments.append('</ul>')
                in_list = False
            html_fragments.append(frag)

    if in_list:
        html_fragments.append('</ul>')

    full_html = '\n'.join(html_fragments)

    # 2. 创建 EPUB 书籍对象
    book = epub.EpubBook()
    book.set_identifier(f'id-{os.path.basename(docx_path)}')
    book.set_title(book_title or os.path.splitext(os.path.basename(docx_path))[0])
    book.set_language('zh')
    book.add_author(author or 'Unknown')

    # 3. 创建章节
    chapter = epub.EpubHtml(
        title='正文',
        file_name='content.xhtml',
        lang='zh'
    )
    chapter.content = f'<html><body>{full_html}</body></html>'
    book.add_item(chapter)

    # 4. 设置目录和书脊
    book.toc = (chapter,)
    book.spine = ['nav', chapter]

    # 5. 添加默认导航样式
    style = epub.EpubItem(
        uid='style_default',
        file_name='style/default.css',
        media_type='text/css',
        content='body { font-family: serif; line-height: 1.6; }'
    )
    book.add_item(style)
    chapter.add_item(style)

    # 6. 写入文件
    epub.write_epub(epub_path, book)
    print(f'✅ EPUB 已生成：{epub_path}')

docx_to_epub_pure(
    'input.docx',
    'output_pure.epub',
    book_title='纯 Python 转换示例',
    author='Your Name'
)