import PyPDF2
import os
import sys

pdf_path = r'D:\Code\SecMPS\doc\对接文档\MC4.0对外API.pdf'
output_path = r'D:\Code\SecMPS\doc\对接文档\MC4.0对外API.md'

try:
    print(f'正在读取: {pdf_path}')
    
    with open(pdf_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfReader(file)
        num_pages = len(pdf_reader.pages)
        
        print(f'PDF总页数: {num_pages}')
        
        full_text = []
        full_text.append('# MC4.0对外API文档\n')
        full_text.append(f'\n> 原文档页数: {num_pages} 页\n')
        full_text.append('---\n\n')
        
        for page_num in range(num_pages):
            page = pdf_reader.pages[page_num]
            text = page.extract_text()
            if text and text.strip():
                full_text.append(f'## 第 {page_num + 1} 页\n')
                full_text.append(text)
                full_text.append('\n---\n\n')
        
        with open(output_path, 'w', encoding='utf-8') as md_file:
            md_file.write('\n'.join(full_text))
        
        print(f'转换完成！已保存至: {output_path}')
        
except Exception as e:
    print(f'错误: {e}')
    sys.exit(1)