four-level-schedule/parser/utils/mime_detector.py

import filetype
import os


class MimeDetector:
    """文件MIME类型检测工具"""
    
    def __init__(self):
        pass
    
    def detect(self, file_path: str) -> str:
        """
        检测文件的MIME类型
        
        Args:
            file_path: 文件路径
            
        Returns:
            str: MIME类型字符串
        """
        try:
            # 使用filetype库检测文件类型
            kind = filetype.guess(file_path)
            if kind:
                return kind.mime
            else:
                # 如果filetype无法检测，根据文件扩展名猜测
                ext = os.path.splitext(file_path)[1].lower()
                ext_to_mime = {
                    '.txt': 'text/plain',
                    '.md': 'text/markdown',
                    '.pdf': 'application/pdf',
                    '.docx': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
                    '.doc': 'application/msword',
                    '.xlsx': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
                    '.xls': 'application/vnd.ms-excel',
                    '.pptx': 'application/vnd.openxmlformats-officedocument.presentationml.presentation',
                    '.ppt': 'application/vnd.ms-powerpoint',
                    '.jpg': 'image/jpeg',
                    '.jpeg': 'image/jpeg',
                    '.png': 'image/png',
                    '.gif': 'image/gif',
                    '.wav': 'audio/wav',
                    '.mp3': 'audio/mpeg',
                    '.mp4': 'video/mp4',
                    '.avi': 'video/x-msvideo',
                    '.mov': 'video/quicktime'
                }
                return ext_to_mime.get(ext, 'application/octet-stream')
        except Exception as e:
            raise Exception(f"文件类型检测失败: {str(e)}")