Python 使用 Flask 实现 DOCX 转 Markdown 及图片提取

项目简介

• 功能：上传 .docx → 返回 Markdown 文本 + 提取图片（通过 API 提供图片访问 URL），前端支持预览与打包下载 ZIP。
• 适用场景：将 Word 文档内容迁移到博客、技术文档、知识库时快速生成 Markdown。

环境与依赖

• Python 3.8+（示例中也可用 Python 3.13）
• 依赖见 requirements.txt：

python-docx==0.8.11
Flask==2.3.0
Flask-CORS==4.0.0
Werkzeug==2.3.0

• 安装命令：

python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

项目结构（简要）

• app.py — Flask 后端，负责接收上传、解析 DOCX、提取图片并返回 Markdown。
• templates/index.html — 前端页面，基于 Vue 3，提供上传、展示与下载功能。
• uploads/ — 存放上传的文件与提取的图片（运行时生成）。

完整代码

#!/usr/bin/env python3
""" DOCX 转 Markdown 的 Flask API 后端 """
from flask import Flask, request, jsonify, send_file, render_template
from flask_cors import CORS
from docx import Document
import os
import io
import json
from pathlib import Path
from werkzeug.utils import secure_filename

app = Flask(__name__, static_folder='templates')
CORS(app)

# 配置上传文件夹
UPLOAD_FOLDER = 'uploads'
ALLOWED_EXTENSIONS = {'docx', 'doc'}
MAX_FILE_SIZE =  *  *  

  os.path.exists(UPLOAD_FOLDER):
    os.makedirs(UPLOAD_FOLDER)

app.config[] = UPLOAD_FOLDER
app.config[] = MAX_FILE_SIZE

 ():
    
       filename  filename.rsplit(, )[].lower()  ALLOWED_EXTENSIONS

 ():
    
    images = []
     drawing  run.element.findall():
         blip  drawing.findall():
            embed_id = blip.get()
             embed_id:
                :
                    
                    image_part = run.part.rels[embed_id].target_part
                    image_data = image_part.blob
                    
                    content_type = image_part.content_type
                    ext_map = {
                        : ,
                        : ,
                        : ,
                        : ,
                        : ,
                        : 
                    }
                    ext = ext_map.get(content_type, )
                    image_counter += 
                    image_filename = 
                    image_path = os.path.join(image_dir, image_filename)
                    
                     (image_path, )  f:
                        f.write(image_data)
                    images.append({
                        : image_filename,
                        : image_path,
                        : image_counter
                    })
                 Exception  e:
                    
     images, image_counter

 ():
    
     image_dir  :
        image_dir = os.path.join(UPLOAD_FOLDER, )
      os.path.exists(image_dir):
        os.makedirs(image_dir)

    
    doc = Document(docx_path)
    markdown_content = []
    image_counter = 

    
     para  doc.paragraphs:
        
         run  para.runs:
            images, image_counter = extract_images_from_run(run, image_dir, image_counter)
             img  images:
                rel_path = os.path.join(, img[])
                markdown_content.append()
        markdown_content.append()

        text = para.text.strip()
          text:
            markdown_content.append()
            

        
        style = para.style.name  para.style  

        
           style:
            markdown_content.append()
           style:
            markdown_content.append()
           style:
            markdown_content.append()
           style:
            markdown_content.append()
           style:
            markdown_content.append()
           style:
            markdown_content.append()
        :
            
            formatted_text = process_runs(para.runs)
             formatted_text:
                markdown_content.append(formatted_text)
            :
                markdown_content.append(text)

    
     table  doc.tables:
        markdown_content.append()
        markdown_table, image_counter = convert_table_to_markdown(table, image_dir, image_counter)
        markdown_content.extend(markdown_table)
        markdown_content.append()

    result = .join(markdown_content)
     result, image_counter

 ():
    
    result = []
     run  runs:
        text = run.text
          text:
            
        
         run.bold:
            text = 
        
         run.italic:
            text = 
        
         run.underline:
            text = 
        result.append(text)
     .join(result).strip()

 ():
    
    markdown_lines = []
    
     i, row  (table.rows):
        cells = row.cells
        row_content = []
         cell  cells:
            
            cell_parts = []
             para  cell.paragraphs:
                
                 run  para.runs:
                    images, image_counter = extract_images_from_run(run, image_dir, image_counter)
                     img  images:
                        rel_path = os.path.join(, img[])
                        cell_parts.append()
                para_text = para.text.strip()
                 para_text:
                    cell_parts.append(para_text)
            cell_text = .join(cell_parts).strip()
            row_content.append(cell_text)

        
        markdown_lines.append( + .join(row_content) + )

        
         i == :
            separator =  + .join([  _  row_content]) + 
            markdown_lines.append(separator)

     markdown_lines, image_counter


 ():
    
     send_file(, mimetype=)


 ():
    
     jsonify({: })


 ():
    
    :
        
            request.files:
             jsonify({: , : }), 
        file = request.files[]
         file.filename == :
             jsonify({: , : }), 
          allowed_file(file.filename):
             jsonify({: , : }), 

        
        filename = secure_filename(file.filename)
        filepath = os.path.join(app.config[], filename)
        file.save(filepath)

        
        image_dir = os.path.join(app.config[], Path(filename).stem + )

        
        markdown_content, image_count = convert_docx_to_markdown(filepath, image_dir)

        
        images = []
         os.path.exists(image_dir):
             img_file  os.listdir(image_dir):
                 os.path.isfile(os.path.join(image_dir, img_file)):
                    images.append({
                        : img_file,
                        : 
                    })

        
         img  images:
            
            old_path = 
            markdown_content = markdown_content.replace(old_path, img[])

        
        :
            os.remove(filepath)
        :
            

         jsonify({
            : ,
            : markdown_content,
            : images,
            : image_count
        })
     Exception  e:
         jsonify({: , : (e)}), 


 ():
    
    :
        full_path = os.path.join(app.config[], filepath)
        
          os.path.abspath(full_path).startswith(os.path.abspath(app.config[])):
             jsonify({: , : }), 
          os.path.exists(full_path):
             jsonify({: , : }), 
         send_file(full_path)
     Exception  e:
         jsonify({: , : (e)}), 

 __name__ == :
    app.run(debug=, host=, port=)