使用.NET,如何根据文件签名而不是扩展名找到文件的 mime 类型

StackOverflow https://stackoverflow.com/questions/58510

  •  09-06-2019
  •  | 
  •  

我正在寻找一种简单的方法来获取文件扩展名不正确或未给出的 mime 类型,类似于 这个问题 仅在.Net 中。

有帮助吗?

解决方案

在Urlmon.dll中,有一个函数叫做 FindMimeFromData.

从文档中

MIME 类型检测或“数据嗅探”是指从二进制数据确定适当的 MIME 类型的过程。最终结果取决于服务器提供的 MIME 类型标头、文件扩展名和/或数据本身的组合。通常,只有前 256 个字节的数据是重要的。

因此,从文件中读取前(最多)256 个字节并将其传递给 FindMimeFromData.

其他提示

我最终确实使用了urlmon.dll。我以为会有更简单的方法,但这可行。我添加代码是为了帮助其他人,并允许我在需要时再次找到它。

using System.Runtime.InteropServices;

...

    [DllImport(@"urlmon.dll", CharSet = CharSet.Auto)]
    private extern static System.UInt32 FindMimeFromData(
        System.UInt32 pBC,
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl,
        [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer,
        System.UInt32 cbSize,
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed,
        System.UInt32 dwMimeFlags,
        out System.UInt32 ppwzMimeOut,
        System.UInt32 dwReserverd
    );

    public static string getMimeFromFile(string filename)
    {
        if (!File.Exists(filename))
            throw new FileNotFoundException(filename + " not found");

        byte[] buffer = new byte[256];
        using (FileStream fs = new FileStream(filename, FileMode.Open))
        {
            if (fs.Length >= 256)
                fs.Read(buffer, 0, 256);
            else
                fs.Read(buffer, 0, (int)fs.Length);
        }
        try
        {
            System.UInt32 mimetype;
            FindMimeFromData(0, null, buffer, 256, null, 0, out mimetype, 0);
            System.IntPtr mimeTypePtr = new IntPtr(mimetype);
            string mime = Marshal.PtrToStringUni(mimeTypePtr);
            Marshal.FreeCoTaskMem(mimeTypePtr);
            return mime;
        }
        catch (Exception e)
        {
            return "unknown/unknown";
        }
    }

我找到了一个硬编码的解决方案,我希望我能帮助别人:

public static class MIMEAssistant
{
  private static readonly Dictionary<string, string> MIMETypesDictionary = new Dictionary<string, string>
  {
    {"ai", "application/postscript"},
    {"aif", "audio/x-aiff"},
    {"aifc", "audio/x-aiff"},
    {"aiff", "audio/x-aiff"},
    {"asc", "text/plain"},
    {"atom", "application/atom+xml"},
    {"au", "audio/basic"},
    {"avi", "video/x-msvideo"},
    {"bcpio", "application/x-bcpio"},
    {"bin", "application/octet-stream"},
    {"bmp", "image/bmp"},
    {"cdf", "application/x-netcdf"},
    {"cgm", "image/cgm"},
    {"class", "application/octet-stream"},
    {"cpio", "application/x-cpio"},
    {"cpt", "application/mac-compactpro"},
    {"csh", "application/x-csh"},
    {"css", "text/css"},
    {"dcr", "application/x-director"},
    {"dif", "video/x-dv"},
    {"dir", "application/x-director"},
    {"djv", "image/vnd.djvu"},
    {"djvu", "image/vnd.djvu"},
    {"dll", "application/octet-stream"},
    {"dmg", "application/octet-stream"},
    {"dms", "application/octet-stream"},
    {"doc", "application/msword"},
    {"docx","application/vnd.openxmlformats-officedocument.wordprocessingml.document"},
    {"dotx", "application/vnd.openxmlformats-officedocument.wordprocessingml.template"},
    {"docm","application/vnd.ms-word.document.macroEnabled.12"},
    {"dotm","application/vnd.ms-word.template.macroEnabled.12"},
    {"dtd", "application/xml-dtd"},
    {"dv", "video/x-dv"},
    {"dvi", "application/x-dvi"},
    {"dxr", "application/x-director"},
    {"eps", "application/postscript"},
    {"etx", "text/x-setext"},
    {"exe", "application/octet-stream"},
    {"ez", "application/andrew-inset"},
    {"gif", "image/gif"},
    {"gram", "application/srgs"},
    {"grxml", "application/srgs+xml"},
    {"gtar", "application/x-gtar"},
    {"hdf", "application/x-hdf"},
    {"hqx", "application/mac-binhex40"},
    {"htm", "text/html"},
    {"html", "text/html"},
    {"ice", "x-conference/x-cooltalk"},
    {"ico", "image/x-icon"},
    {"ics", "text/calendar"},
    {"ief", "image/ief"},
    {"ifb", "text/calendar"},
    {"iges", "model/iges"},
    {"igs", "model/iges"},
    {"jnlp", "application/x-java-jnlp-file"},
    {"jp2", "image/jp2"},
    {"jpe", "image/jpeg"},
    {"jpeg", "image/jpeg"},
    {"jpg", "image/jpeg"},
    {"js", "application/x-javascript"},
    {"kar", "audio/midi"},
    {"latex", "application/x-latex"},
    {"lha", "application/octet-stream"},
    {"lzh", "application/octet-stream"},
    {"m3u", "audio/x-mpegurl"},
    {"m4a", "audio/mp4a-latm"},
    {"m4b", "audio/mp4a-latm"},
    {"m4p", "audio/mp4a-latm"},
    {"m4u", "video/vnd.mpegurl"},
    {"m4v", "video/x-m4v"},
    {"mac", "image/x-macpaint"},
    {"man", "application/x-troff-man"},
    {"mathml", "application/mathml+xml"},
    {"me", "application/x-troff-me"},
    {"mesh", "model/mesh"},
    {"mid", "audio/midi"},
    {"midi", "audio/midi"},
    {"mif", "application/vnd.mif"},
    {"mov", "video/quicktime"},
    {"movie", "video/x-sgi-movie"},
    {"mp2", "audio/mpeg"},
    {"mp3", "audio/mpeg"},
    {"mp4", "video/mp4"},
    {"mpe", "video/mpeg"},
    {"mpeg", "video/mpeg"},
    {"mpg", "video/mpeg"},
    {"mpga", "audio/mpeg"},
    {"ms", "application/x-troff-ms"},
    {"msh", "model/mesh"},
    {"mxu", "video/vnd.mpegurl"},
    {"nc", "application/x-netcdf"},
    {"oda", "application/oda"},
    {"ogg", "application/ogg"},
    {"pbm", "image/x-portable-bitmap"},
    {"pct", "image/pict"},
    {"pdb", "chemical/x-pdb"},
    {"pdf", "application/pdf"},
    {"pgm", "image/x-portable-graymap"},
    {"pgn", "application/x-chess-pgn"},
    {"pic", "image/pict"},
    {"pict", "image/pict"},
    {"png", "image/png"}, 
    {"pnm", "image/x-portable-anymap"},
    {"pnt", "image/x-macpaint"},
    {"pntg", "image/x-macpaint"},
    {"ppm", "image/x-portable-pixmap"},
    {"ppt", "application/vnd.ms-powerpoint"},
    {"pptx","application/vnd.openxmlformats-officedocument.presentationml.presentation"},
    {"potx","application/vnd.openxmlformats-officedocument.presentationml.template"},
    {"ppsx","application/vnd.openxmlformats-officedocument.presentationml.slideshow"},
    {"ppam","application/vnd.ms-powerpoint.addin.macroEnabled.12"},
    {"pptm","application/vnd.ms-powerpoint.presentation.macroEnabled.12"},
    {"potm","application/vnd.ms-powerpoint.template.macroEnabled.12"},
    {"ppsm","application/vnd.ms-powerpoint.slideshow.macroEnabled.12"},
    {"ps", "application/postscript"},
    {"qt", "video/quicktime"},
    {"qti", "image/x-quicktime"},
    {"qtif", "image/x-quicktime"},
    {"ra", "audio/x-pn-realaudio"},
    {"ram", "audio/x-pn-realaudio"},
    {"ras", "image/x-cmu-raster"},
    {"rdf", "application/rdf+xml"},
    {"rgb", "image/x-rgb"},
    {"rm", "application/vnd.rn-realmedia"},
    {"roff", "application/x-troff"},
    {"rtf", "text/rtf"},
    {"rtx", "text/richtext"},
    {"sgm", "text/sgml"},
    {"sgml", "text/sgml"},
    {"sh", "application/x-sh"},
    {"shar", "application/x-shar"},
    {"silo", "model/mesh"},
    {"sit", "application/x-stuffit"},
    {"skd", "application/x-koan"},
    {"skm", "application/x-koan"},
    {"skp", "application/x-koan"},
    {"skt", "application/x-koan"},
    {"smi", "application/smil"},
    {"smil", "application/smil"},
    {"snd", "audio/basic"},
    {"so", "application/octet-stream"},
    {"spl", "application/x-futuresplash"},
    {"src", "application/x-wais-source"},
    {"sv4cpio", "application/x-sv4cpio"},
    {"sv4crc", "application/x-sv4crc"},
    {"svg", "image/svg+xml"},
    {"swf", "application/x-shockwave-flash"},
    {"t", "application/x-troff"},
    {"tar", "application/x-tar"},
    {"tcl", "application/x-tcl"},
    {"tex", "application/x-tex"},
    {"texi", "application/x-texinfo"},
    {"texinfo", "application/x-texinfo"},
    {"tif", "image/tiff"},
    {"tiff", "image/tiff"},
    {"tr", "application/x-troff"},
    {"tsv", "text/tab-separated-values"},
    {"txt", "text/plain"},
    {"ustar", "application/x-ustar"},
    {"vcd", "application/x-cdlink"},
    {"vrml", "model/vrml"},
    {"vxml", "application/voicexml+xml"},
    {"wav", "audio/x-wav"},
    {"wbmp", "image/vnd.wap.wbmp"},
    {"wbmxl", "application/vnd.wap.wbxml"},
    {"wml", "text/vnd.wap.wml"},
    {"wmlc", "application/vnd.wap.wmlc"},
    {"wmls", "text/vnd.wap.wmlscript"},
    {"wmlsc", "application/vnd.wap.wmlscriptc"},
    {"wrl", "model/vrml"},
    {"xbm", "image/x-xbitmap"},
    {"xht", "application/xhtml+xml"},
    {"xhtml", "application/xhtml+xml"},
    {"xls", "application/vnd.ms-excel"},                        
    {"xml", "application/xml"},
    {"xpm", "image/x-xpixmap"},
    {"xsl", "application/xml"},
    {"xlsx","application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"},
    {"xltx","application/vnd.openxmlformats-officedocument.spreadsheetml.template"},
    {"xlsm","application/vnd.ms-excel.sheet.macroEnabled.12"},
    {"xltm","application/vnd.ms-excel.template.macroEnabled.12"},
    {"xlam","application/vnd.ms-excel.addin.macroEnabled.12"},
    {"xlsb","application/vnd.ms-excel.sheet.binary.macroEnabled.12"},
    {"xslt", "application/xslt+xml"},
    {"xul", "application/vnd.mozilla.xul+xml"},
    {"xwd", "image/x-xwindowdump"},
    {"xyz", "chemical/x-xyz"},
    {"zip", "application/zip"}
  };

  public static string GetMIMEType(string fileName)
  {
    //get file extension
    string extension = Path.GetExtension(fileName).ToLowerInvariant();

    if (extension.Length > 0 && 
        MIMETypesDictionary.ContainsKey(extension.Remove(0, 1)))
    {
      return MIMETypesDictionary[extension.Remove(0, 1)];
    }
    return "unknown/unknown";
  }
}

编辑:只需使用 哑剧侦探

我使用字节数组序列来确定给定文件的正确 MIME 类型。与仅查看文件名的文件扩展名相比,这样做的优点是,如果用户要重命名文件以绕过某些文件类型上传限制,则文件扩展名将无法捕获这一点。另一方面,通过字节数组获取文件签名将阻止这种恶作剧行为的发生。

下面是一个 C# 示例:

public class MimeType
{
    private static readonly byte[] BMP = { 66, 77 };
    private static readonly byte[] DOC = { 208, 207, 17, 224, 161, 177, 26, 225 };
    private static readonly byte[] EXE_DLL = { 77, 90 };
    private static readonly byte[] GIF = { 71, 73, 70, 56 };
    private static readonly byte[] ICO = { 0, 0, 1, 0 };
    private static readonly byte[] JPG = { 255, 216, 255 };
    private static readonly byte[] MP3 = { 255, 251, 48 };
    private static readonly byte[] OGG = { 79, 103, 103, 83, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0 };
    private static readonly byte[] PDF = { 37, 80, 68, 70, 45, 49, 46 };
    private static readonly byte[] PNG = { 137, 80, 78, 71, 13, 10, 26, 10, 0, 0, 0, 13, 73, 72, 68, 82 };
    private static readonly byte[] RAR = { 82, 97, 114, 33, 26, 7, 0 };
    private static readonly byte[] SWF = { 70, 87, 83 };
    private static readonly byte[] TIFF = { 73, 73, 42, 0 };
    private static readonly byte[] TORRENT = { 100, 56, 58, 97, 110, 110, 111, 117, 110, 99, 101 };
    private static readonly byte[] TTF = { 0, 1, 0, 0, 0 };
    private static readonly byte[] WAV_AVI = { 82, 73, 70, 70 };
    private static readonly byte[] WMV_WMA = { 48, 38, 178, 117, 142, 102, 207, 17, 166, 217, 0, 170, 0, 98, 206, 108 };
    private static readonly byte[] ZIP_DOCX = { 80, 75, 3, 4 };

    public static string GetMimeType(byte[] file, string fileName)
    {

        string mime = "application/octet-stream"; //DEFAULT UNKNOWN MIME TYPE

        //Ensure that the filename isn't empty or null
        if (string.IsNullOrWhiteSpace(fileName))
        {
            return mime;
        }

        //Get the file extension
        string extension = Path.GetExtension(fileName) == null
                               ? string.Empty
                               : Path.GetExtension(fileName).ToUpper();

        //Get the MIME Type
        if (file.Take(2).SequenceEqual(BMP))
        {
            mime = "image/bmp";
        }
        else if (file.Take(8).SequenceEqual(DOC))
        {
            mime = "application/msword";
        }
        else if (file.Take(2).SequenceEqual(EXE_DLL))
        {
            mime = "application/x-msdownload"; //both use same mime type
        }
        else if (file.Take(4).SequenceEqual(GIF))
        {
            mime = "image/gif";
        }
        else if (file.Take(4).SequenceEqual(ICO))
        {
            mime = "image/x-icon";
        }
        else if (file.Take(3).SequenceEqual(JPG))
        {
            mime = "image/jpeg";
        }
        else if (file.Take(3).SequenceEqual(MP3))
        {
            mime = "audio/mpeg";
        }
        else if (file.Take(14).SequenceEqual(OGG))
        {
            if (extension == ".OGX")
            {
                mime = "application/ogg";
            }
            else if (extension == ".OGA")
            {
                mime = "audio/ogg";
            }
            else
            {
                mime = "video/ogg";
            }
        }
        else if (file.Take(7).SequenceEqual(PDF))
        {
            mime = "application/pdf";
        }
        else if (file.Take(16).SequenceEqual(PNG))
        {
            mime = "image/png";
        }
        else if (file.Take(7).SequenceEqual(RAR))
        {
            mime = "application/x-rar-compressed";
        }
        else if (file.Take(3).SequenceEqual(SWF))
        {
            mime = "application/x-shockwave-flash";
        }
        else if (file.Take(4).SequenceEqual(TIFF))
        {
            mime = "image/tiff";
        }
        else if (file.Take(11).SequenceEqual(TORRENT))
        {
            mime = "application/x-bittorrent";
        }
        else if (file.Take(5).SequenceEqual(TTF))
        {
            mime = "application/x-font-ttf";
        }
        else if (file.Take(4).SequenceEqual(WAV_AVI))
        {
            mime = extension == ".AVI" ? "video/x-msvideo" : "audio/x-wav";
        }
        else if (file.Take(16).SequenceEqual(WMV_WMA))
        {
            mime = extension == ".WMA" ? "audio/x-ms-wma" : "video/x-ms-wmv";
        }
        else if (file.Take(4).SequenceEqual(ZIP_DOCX))
        {
            mime = extension == ".DOCX" ? "application/vnd.openxmlformats-officedocument.wordprocessingml.document" : "application/x-zip-compressed";
        }

        return mime;
    }


}

请注意,我以不同的方式处理 DOCX 文件类型,因为 DOCX 实际上只是一个 ZIP 文件。在这种情况下,一旦验证文件扩展名具有该序列,我只需检查文件扩展名。对于某些人来说,这个示例还远未完成,但您可以轻松添加自己的示例。

如果想添加更多的MIME类型,可以获取多种不同文件类型的字节数组序列 从这里. 。还, 这是另一个很好的资源 关于文件签名。

如果其他方法都失败,我经常做的就是逐步浏览我正在寻找的特定类型的多个文件,并在文件的字节序列中寻找模式。最终,这仍然是基本验证,并不能用于100%确定文件类型的证明。

如果您使用的是 .NET Framework 4.5 或更高版本,现在有一个 MimeMapping.GetMimeMapping(filename) 方法,它将返回一个字符串,其中包含传递的文件名的正确 Mime 映射。请注意,这使用文件扩展名,而不是文件本身中的数据。

文档位于 http://msdn.microsoft.com/en-us/library/system.web.mimemapping.getmimemapping

您也可以在注册表中查看。

    using System.IO;
    using Microsoft.Win32;

    string GetMimeType(FileInfo fileInfo)
    {
        string mimeType = "application/unknown";

        RegistryKey regKey = Registry.ClassesRoot.OpenSubKey(
            fileInfo.Extension.ToLower()
            );

        if(regKey != null)
        {
            object contentType = regKey.GetValue("Content Type");

            if(contentType != null)
                mimeType = contentType.ToString();
        }

        return mimeType;
    }

不管怎样,您都必须进入 MIME 数据库 - 无论它们是从扩展名还是幻数映射的,这都有点微不足道 - Windows 注册表就是这样的地方之一。对于独立于平台的解决方案,必须将此数据库与代码一起提供(或作为独立库)。

我使用混合解决方案:

    using System.Runtime.InteropServices;

    [DllImport (@"urlmon.dll", CharSet = CharSet.Auto)]
    private extern static System.UInt32 FindMimeFromData(
        System.UInt32 pBC, 
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl,
        [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer,
        System.UInt32 cbSize,
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed,
        System.UInt32 dwMimeFlags,
        out System.UInt32 ppwzMimeOut,
        System.UInt32 dwReserverd
    );

    private string GetMimeFromRegistry (string Filename)
    {
        string mime = "application/octetstream";
        string ext = System.IO.Path.GetExtension(Filename).ToLower();
        Microsoft.Win32.RegistryKey rk = Microsoft.Win32.Registry.ClassesRoot.OpenSubKey(ext);
        if (rk != null && rk.GetValue("Content Type") != null)
            mime = rk.GetValue("Content Type").ToString();
        return mime;
    }

    public string GetMimeTypeFromFileAndRegistry (string filename)
    {
        if (!File.Exists(filename))
        {
           return GetMimeFromRegistry (filename);
        }

        byte[] buffer = new byte[256];

        using (FileStream fs = new FileStream(filename, FileMode.Open))
        {
            if (fs.Length >= 256)
                fs.Read(buffer, 0, 256);
            else
                fs.Read(buffer, 0, (int)fs.Length);
        }

        try
        {            
            System.UInt32 mimetype;

            FindMimeFromData(0, null, buffer, 256, null, 0, out mimetype, 0);

            System.IntPtr mimeTypePtr = new IntPtr(mimetype);

            string mime = Marshal.PtrToStringUni(mimeTypePtr);

            Marshal.FreeCoTaskMem(mimeTypePtr);

            if (string.IsNullOrWhiteSpace (mime) || 
                mime =="text/plain" || mime == "application/octet-stream")                    
            {
                return GetMimeFromRegistry (filename);
            }

            return mime;
        }
        catch (Exception e)
        {
            return GetMimeFromRegistry (filename);
        }
    }

我发现这个很有用。对于 VB.NET 开发人员:

    Public Shared Function GetFromFileName(ByVal fileName As String) As String
        Return GetFromExtension(Path.GetExtension(fileName).Remove(0, 1))
    End Function

    Public Shared Function GetFromExtension(ByVal extension As String) As String
        If extension.StartsWith("."c) Then
            extension = extension.Remove(0, 1)
        End If

        If MIMETypesDictionary.ContainsKey(extension) Then
            Return MIMETypesDictionary(extension)
        End If

        Return "unknown/unknown"
    End Function

    Private Shared ReadOnly MIMETypesDictionary As New Dictionary(Of String, String)() From { _
         {"ai", "application/postscript"}, _
         {"aif", "audio/x-aiff"}, _
         {"aifc", "audio/x-aiff"}, _
         {"aiff", "audio/x-aiff"}, _
         {"asc", "text/plain"}, _
         {"atom", "application/atom+xml"}, _
         {"au", "audio/basic"}, _
         {"avi", "video/x-msvideo"}, _
         {"bcpio", "application/x-bcpio"}, _
         {"bin", "application/octet-stream"}, _
         {"bmp", "image/bmp"}, _
         {"cdf", "application/x-netcdf"}, _
         {"cgm", "image/cgm"}, _
         {"class", "application/octet-stream"}, _
         {"cpio", "application/x-cpio"}, _
         {"cpt", "application/mac-compactpro"}, _
         {"csh", "application/x-csh"}, _
         {"css", "text/css"}, _
         {"dcr", "application/x-director"}, _
         {"dif", "video/x-dv"}, _
         {"dir", "application/x-director"}, _
         {"djv", "image/vnd.djvu"}, _
         {"djvu", "image/vnd.djvu"}, _
         {"dll", "application/octet-stream"}, _
         {"dmg", "application/octet-stream"}, _
         {"dms", "application/octet-stream"}, _
         {"doc", "application/msword"}, _
         {"dtd", "application/xml-dtd"}, _
         {"dv", "video/x-dv"}, _
         {"dvi", "application/x-dvi"}, _
         {"dxr", "application/x-director"}, _
         {"eps", "application/postscript"}, _
         {"etx", "text/x-setext"}, _
         {"exe", "application/octet-stream"}, _
         {"ez", "application/andrew-inset"}, _
         {"gif", "image/gif"}, _
         {"gram", "application/srgs"}, _
         {"grxml", "application/srgs+xml"}, _
         {"gtar", "application/x-gtar"}, _
         {"hdf", "application/x-hdf"}, _
         {"hqx", "application/mac-binhex40"}, _
         {"htm", "text/html"}, _
         {"html", "text/html"}, _
         {"ice", "x-conference/x-cooltalk"}, _
         {"ico", "image/x-icon"}, _
         {"ics", "text/calendar"}, _
         {"ief", "image/ief"}, _
         {"ifb", "text/calendar"}, _
         {"iges", "model/iges"}, _
         {"igs", "model/iges"}, _
         {"jnlp", "application/x-java-jnlp-file"}, _
         {"jp2", "image/jp2"}, _
         {"jpe", "image/jpeg"}, _
         {"jpeg", "image/jpeg"}, _
         {"jpg", "image/jpeg"}, _
         {"js", "application/x-javascript"}, _
         {"kar", "audio/midi"}, _
         {"latex", "application/x-latex"}, _
         {"lha", "application/octet-stream"}, _
         {"lzh", "application/octet-stream"}, _
         {"m3u", "audio/x-mpegurl"}, _
         {"m4a", "audio/mp4a-latm"}, _
         {"m4b", "audio/mp4a-latm"}, _
         {"m4p", "audio/mp4a-latm"}, _
         {"m4u", "video/vnd.mpegurl"}, _
         {"m4v", "video/x-m4v"}, _
         {"mac", "image/x-macpaint"}, _
         {"man", "application/x-troff-man"}, _
         {"mathml", "application/mathml+xml"}, _
         {"me", "application/x-troff-me"}, _
         {"mesh", "model/mesh"}, _
         {"mid", "audio/midi"}, _
         {"midi", "audio/midi"}, _
         {"mif", "application/vnd.mif"}, _
         {"mov", "video/quicktime"}, _
         {"movie", "video/x-sgi-movie"}, _
         {"mp2", "audio/mpeg"}, _
         {"mp3", "audio/mpeg"}, _
         {"mp4", "video/mp4"}, _
         {"mpe", "video/mpeg"}, _
         {"mpeg", "video/mpeg"}, _
         {"mpg", "video/mpeg"}, _
         {"mpga", "audio/mpeg"}, _
         {"ms", "application/x-troff-ms"}, _
         {"msh", "model/mesh"}, _
         {"mxu", "video/vnd.mpegurl"}, _
         {"nc", "application/x-netcdf"}, _
         {"oda", "application/oda"}, _
         {"ogg", "application/ogg"}, _
         {"pbm", "image/x-portable-bitmap"}, _
         {"pct", "image/pict"}, _
         {"pdb", "chemical/x-pdb"}, _
         {"pdf", "application/pdf"}, _
         {"pgm", "image/x-portable-graymap"}, _
         {"pgn", "application/x-chess-pgn"}, _
         {"pic", "image/pict"}, _
         {"pict", "image/pict"}, _
         {"png", "image/png"}, _
         {"pnm", "image/x-portable-anymap"}, _
         {"pnt", "image/x-macpaint"}, _
         {"pntg", "image/x-macpaint"}, _
         {"ppm", "image/x-portable-pixmap"}, _
         {"ppt", "application/vnd.ms-powerpoint"}, _
         {"ps", "application/postscript"}, _
         {"qt", "video/quicktime"}, _
         {"qti", "image/x-quicktime"}, _
         {"qtif", "image/x-quicktime"}, _
         {"ra", "audio/x-pn-realaudio"}, _
         {"ram", "audio/x-pn-realaudio"}, _
         {"ras", "image/x-cmu-raster"}, _
         {"rdf", "application/rdf+xml"}, _
         {"rgb", "image/x-rgb"}, _
         {"rm", "application/vnd.rn-realmedia"}, _
         {"roff", "application/x-troff"}, _
         {"rtf", "text/rtf"}, _
         {"rtx", "text/richtext"}, _
         {"sgm", "text/sgml"}, _
         {"sgml", "text/sgml"}, _
         {"sh", "application/x-sh"}, _
         {"shar", "application/x-shar"}, _
         {"silo", "model/mesh"}, _
         {"sit", "application/x-stuffit"}, _
         {"skd", "application/x-koan"}, _
         {"skm", "application/x-koan"}, _
         {"skp", "application/x-koan"}, _
         {"skt", "application/x-koan"}, _
         {"smi", "application/smil"}, _
         {"smil", "application/smil"}, _
         {"snd", "audio/basic"}, _
         {"so", "application/octet-stream"}, _
         {"spl", "application/x-futuresplash"}, _
         {"src", "application/x-wais-source"}, _
         {"sv4cpio", "application/x-sv4cpio"}, _
         {"sv4crc", "application/x-sv4crc"}, _
         {"svg", "image/svg+xml"}, _
         {"swf", "application/x-shockwave-flash"}, _
         {"t", "application/x-troff"}, _
         {"tar", "application/x-tar"}, _
         {"tcl", "application/x-tcl"}, _
         {"tex", "application/x-tex"}, _
         {"texi", "application/x-texinfo"}, _
         {"texinfo", "application/x-texinfo"}, _
         {"tif", "image/tiff"}, _
         {"tiff", "image/tiff"}, _
         {"tr", "application/x-troff"}, _
         {"tsv", "text/tab-separated-values"}, _
         {"txt", "text/plain"}, _
         {"ustar", "application/x-ustar"}, _
         {"vcd", "application/x-cdlink"}, _
         {"vrml", "model/vrml"}, _
         {"vxml", "application/voicexml+xml"}, _
         {"wav", "audio/x-wav"}, _
         {"wbmp", "image/vnd.wap.wbmp"}, _
         {"wbmxl", "application/vnd.wap.wbxml"}, _
         {"wml", "text/vnd.wap.wml"}, _
         {"wmlc", "application/vnd.wap.wmlc"}, _
         {"wmls", "text/vnd.wap.wmlscript"}, _
         {"wmlsc", "application/vnd.wap.wmlscriptc"}, _
         {"wrl", "model/vrml"}, _
         {"xbm", "image/x-xbitmap"}, _
         {"xht", "application/xhtml+xml"}, _
         {"xhtml", "application/xhtml+xml"}, _
         {"xls", "application/vnd.ms-excel"}, _
         {"xml", "application/xml"}, _
         {"xpm", "image/x-xpixmap"}, _
         {"xsl", "application/xml"}, _
         {"xslt", "application/xslt+xml"}, _
         {"xul", "application/vnd.mozilla.xul+xml"}, _
         {"xwd", "image/x-xwindowdump"}, _
         {"xyz", "chemical/x-xyz"}, _
         {"zip", "application/zip"} _
        }

我认为正确的答案是 Steve Morgan 和 Serguei 的答案的结合。Internet Explorer 就是这样做的。pinvoke 调用 FindMimeFromData 仅适用于 26 种硬编码 MIME 类型。此外,它还会给出不明确的哑剧类型(例如 text/plain 或者 application/octet-stream)即使可能存在更具体、更合适的哑剧类型。如果它无法提供良好的 mime 类型,您可以转到注册表以获取更具体的 mime 类型。服务器注册表可以有更多最新的 MIME 类型。

参考: http://msdn.microsoft.com/en-us/library/ms775147(VS.85).aspx

本课程使用之前的答案来尝试 3 种不同的方式:基于扩展、FindMimeFromData API 和使用注册表进行编码。

using System;
using System.Collections.Generic;
using System.IO;
using System.Runtime.InteropServices;

using Microsoft.Win32;

namespace YourNamespace
{
    public static class MimeTypeParser
    {
        [DllImport(@"urlmon.dll", CharSet = CharSet.Auto)]
        private extern static System.UInt32 FindMimeFromData(
                System.UInt32 pBC,
                [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl,
                [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer,
                System.UInt32 cbSize,
                [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed,
                System.UInt32 dwMimeFlags,
                out System.UInt32 ppwzMimeOut,
                System.UInt32 dwReserverd
        );

        public static string GetMimeType(string sFilePath)
        {
            string sMimeType = GetMimeTypeFromList(sFilePath);

            if (String.IsNullOrEmpty(sMimeType))
            {
                sMimeType = GetMimeTypeFromFile(sFilePath);

                if (String.IsNullOrEmpty(sMimeType))
                {
                    sMimeType = GetMimeTypeFromRegistry(sFilePath);
                }
            }

            return sMimeType;
        }

        public static string GetMimeTypeFromList(string sFileNameOrPath)
        {
            string sMimeType = null;
            string sExtensionWithoutDot = Path.GetExtension(sFileNameOrPath).Substring(1).ToLower();

            if (!String.IsNullOrEmpty(sExtensionWithoutDot) && spDicMIMETypes.ContainsKey(sExtensionWithoutDot))
            {
                sMimeType = spDicMIMETypes[sExtensionWithoutDot];
            }

            return sMimeType;
        }

        public static string GetMimeTypeFromRegistry(string sFileNameOrPath)
        {
            string sMimeType = null;
            string sExtension = Path.GetExtension(sFileNameOrPath).ToLower();
            RegistryKey pKey = Registry.ClassesRoot.OpenSubKey(sExtension);

            if (pKey != null && pKey.GetValue("Content Type") != null)
            {
                sMimeType = pKey.GetValue("Content Type").ToString();
            }

            return sMimeType;
        }

        public static string GetMimeTypeFromFile(string sFilePath)
        {
            string sMimeType = null;

            if (File.Exists(sFilePath))
            {
                byte[] abytBuffer = new byte[256];

                using (FileStream pFileStream = new FileStream(sFilePath, FileMode.Open))
                {
                    if (pFileStream.Length >= 256)
                    {
                        pFileStream.Read(abytBuffer, 0, 256);
                    }
                    else
                    {
                        pFileStream.Read(abytBuffer, 0, (int)pFileStream.Length);
                    }
                }

                try
                {
                    UInt32 unMimeType;

                    FindMimeFromData(0, null, abytBuffer, 256, null, 0, out unMimeType, 0);

                    IntPtr pMimeType = new IntPtr(unMimeType);
                    string sMimeTypeFromFile = Marshal.PtrToStringUni(pMimeType);

                    Marshal.FreeCoTaskMem(pMimeType);

                    if (!String.IsNullOrEmpty(sMimeTypeFromFile) && sMimeTypeFromFile != "text/plain" && sMimeTypeFromFile != "application/octet-stream")
                    {
                        sMimeType = sMimeTypeFromFile;
                    }
                }
                catch {}
            }

            return sMimeType;
        }

        private static readonly Dictionary<string, string> spDicMIMETypes = new Dictionary<string, string>
        {
            {"ai", "application/postscript"},
            {"aif", "audio/x-aiff"},
            {"aifc", "audio/x-aiff"},
            {"aiff", "audio/x-aiff"},
            {"asc", "text/plain"},
            {"atom", "application/atom+xml"},
            {"au", "audio/basic"},
            {"avi", "video/x-msvideo"},
            {"bcpio", "application/x-bcpio"},
            {"bin", "application/octet-stream"},
            {"bmp", "image/bmp"},
            {"cdf", "application/x-netcdf"},
            {"cgm", "image/cgm"},
            {"class", "application/octet-stream"},
            {"cpio", "application/x-cpio"},
            {"cpt", "application/mac-compactpro"},
            {"csh", "application/x-csh"},
            {"css", "text/css"},
            {"dcr", "application/x-director"},
            {"dif", "video/x-dv"},
            {"dir", "application/x-director"},
            {"djv", "image/vnd.djvu"},
            {"djvu", "image/vnd.djvu"},
            {"dll", "application/octet-stream"},
            {"dmg", "application/octet-stream"},
            {"dms", "application/octet-stream"},
            {"doc", "application/msword"},
            {"docx","application/vnd.openxmlformats-officedocument.wordprocessingml.document"},
            {"dotx", "application/vnd.openxmlformats-officedocument.wordprocessingml.template"},
            {"docm","application/vnd.ms-word.document.macroEnabled.12"},
            {"dotm","application/vnd.ms-word.template.macroEnabled.12"},
            {"dtd", "application/xml-dtd"},
            {"dv", "video/x-dv"},
            {"dvi", "application/x-dvi"},
            {"dxr", "application/x-director"},
            {"eps", "application/postscript"},
            {"etx", "text/x-setext"},
            {"exe", "application/octet-stream"},
            {"ez", "application/andrew-inset"},
            {"gif", "image/gif"},
            {"gram", "application/srgs"},
            {"grxml", "application/srgs+xml"},
            {"gtar", "application/x-gtar"},
            {"hdf", "application/x-hdf"},
            {"hqx", "application/mac-binhex40"},
            {"htc", "text/x-component"},
            {"htm", "text/html"},
            {"html", "text/html"},
            {"ice", "x-conference/x-cooltalk"},
            {"ico", "image/x-icon"},
            {"ics", "text/calendar"},
            {"ief", "image/ief"},
            {"ifb", "text/calendar"},
            {"iges", "model/iges"},
            {"igs", "model/iges"},
            {"jnlp", "application/x-java-jnlp-file"},
            {"jp2", "image/jp2"},
            {"jpe", "image/jpeg"},
            {"jpeg", "image/jpeg"},
            {"jpg", "image/jpeg"},
            {"js", "application/x-javascript"},
            {"kar", "audio/midi"},
            {"latex", "application/x-latex"},
            {"lha", "application/octet-stream"},
            {"lzh", "application/octet-stream"},
            {"m3u", "audio/x-mpegurl"},
            {"m4a", "audio/mp4a-latm"},
            {"m4b", "audio/mp4a-latm"},
            {"m4p", "audio/mp4a-latm"},
            {"m4u", "video/vnd.mpegurl"},
            {"m4v", "video/x-m4v"},
            {"mac", "image/x-macpaint"},
            {"man", "application/x-troff-man"},
            {"mathml", "application/mathml+xml"},
            {"me", "application/x-troff-me"},
            {"mesh", "model/mesh"},
            {"mid", "audio/midi"},
            {"midi", "audio/midi"},
            {"mif", "application/vnd.mif"},
            {"mov", "video/quicktime"},
            {"movie", "video/x-sgi-movie"},
            {"mp2", "audio/mpeg"},
            {"mp3", "audio/mpeg"},
            {"mp4", "video/mp4"},
            {"mpe", "video/mpeg"},
            {"mpeg", "video/mpeg"},
            {"mpg", "video/mpeg"},
            {"mpga", "audio/mpeg"},
            {"ms", "application/x-troff-ms"},
            {"msh", "model/mesh"},
            {"mxu", "video/vnd.mpegurl"},
            {"nc", "application/x-netcdf"},
            {"oda", "application/oda"},
            {"ogg", "application/ogg"},
            {"pbm", "image/x-portable-bitmap"},
            {"pct", "image/pict"},
            {"pdb", "chemical/x-pdb"},
            {"pdf", "application/pdf"},
            {"pgm", "image/x-portable-graymap"},
            {"pgn", "application/x-chess-pgn"},
            {"pic", "image/pict"},
            {"pict", "image/pict"},
            {"png", "image/png"}, 
            {"pnm", "image/x-portable-anymap"},
            {"pnt", "image/x-macpaint"},
            {"pntg", "image/x-macpaint"},
            {"ppm", "image/x-portable-pixmap"},
            {"ppt", "application/vnd.ms-powerpoint"},
            {"pptx","application/vnd.openxmlformats-officedocument.presentationml.presentation"},
            {"potx","application/vnd.openxmlformats-officedocument.presentationml.template"},
            {"ppsx","application/vnd.openxmlformats-officedocument.presentationml.slideshow"},
            {"ppam","application/vnd.ms-powerpoint.addin.macroEnabled.12"},
            {"pptm","application/vnd.ms-powerpoint.presentation.macroEnabled.12"},
            {"potm","application/vnd.ms-powerpoint.template.macroEnabled.12"},
            {"ppsm","application/vnd.ms-powerpoint.slideshow.macroEnabled.12"},
            {"ps", "application/postscript"},
            {"qt", "video/quicktime"},
            {"qti", "image/x-quicktime"},
            {"qtif", "image/x-quicktime"},
            {"ra", "audio/x-pn-realaudio"},
            {"ram", "audio/x-pn-realaudio"},
            {"ras", "image/x-cmu-raster"},
            {"rdf", "application/rdf+xml"},
            {"rgb", "image/x-rgb"},
            {"rm", "application/vnd.rn-realmedia"},
            {"roff", "application/x-troff"},
            {"rtf", "text/rtf"},
            {"rtx", "text/richtext"},
            {"sgm", "text/sgml"},
            {"sgml", "text/sgml"},
            {"sh", "application/x-sh"},
            {"shar", "application/x-shar"},
            {"silo", "model/mesh"},
            {"sit", "application/x-stuffit"},
            {"skd", "application/x-koan"},
            {"skm", "application/x-koan"},
            {"skp", "application/x-koan"},
            {"skt", "application/x-koan"},
            {"smi", "application/smil"},
            {"smil", "application/smil"},
            {"snd", "audio/basic"},
            {"so", "application/octet-stream"},
            {"spl", "application/x-futuresplash"},
            {"src", "application/x-wais-source"},
            {"sv4cpio", "application/x-sv4cpio"},
            {"sv4crc", "application/x-sv4crc"},
            {"svg", "image/svg+xml"},
            {"swf", "application/x-shockwave-flash"},
            {"t", "application/x-troff"},
            {"tar", "application/x-tar"},
            {"tcl", "application/x-tcl"},
            {"tex", "application/x-tex"},
            {"texi", "application/x-texinfo"},
            {"texinfo", "application/x-texinfo"},
            {"tif", "image/tiff"},
            {"tiff", "image/tiff"},
            {"tr", "application/x-troff"},
            {"tsv", "text/tab-separated-values"},
            {"txt", "text/plain"},
            {"ustar", "application/x-ustar"},
            {"vcd", "application/x-cdlink"},
            {"vrml", "model/vrml"},
            {"vxml", "application/voicexml+xml"},
            {"wav", "audio/x-wav"},
            {"wbmp", "image/vnd.wap.wbmp"},
            {"wbmxl", "application/vnd.wap.wbxml"},
            {"wml", "text/vnd.wap.wml"},
            {"wmlc", "application/vnd.wap.wmlc"},
            {"wmls", "text/vnd.wap.wmlscript"},
            {"wmlsc", "application/vnd.wap.wmlscriptc"},
            {"wrl", "model/vrml"},
            {"xbm", "image/x-xbitmap"},
            {"xht", "application/xhtml+xml"},
            {"xhtml", "application/xhtml+xml"},
            {"xls", "application/vnd.ms-excel"},                                                
            {"xml", "application/xml"},
            {"xpm", "image/x-xpixmap"},
            {"xsl", "application/xml"},
            {"xlsx","application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"},
            {"xltx","application/vnd.openxmlformats-officedocument.spreadsheetml.template"},
            {"xlsm","application/vnd.ms-excel.sheet.macroEnabled.12"},
            {"xltm","application/vnd.ms-excel.template.macroEnabled.12"},
            {"xlam","application/vnd.ms-excel.addin.macroEnabled.12"},
            {"xlsb","application/vnd.ms-excel.sheet.binary.macroEnabled.12"},
            {"xslt", "application/xslt+xml"},
            {"xul", "application/vnd.mozilla.xul+xml"},
            {"xwd", "image/x-xwindowdump"},
            {"xyz", "chemical/x-xyz"},
            {"zip", "application/zip"}
        };
    }
}

我遇到了同样的问题,最终选择了我自己的 Kirk Ba​​ucom 解决方案, 在这里找到.

在我看来,这是一个有人编写在线查找服务的机会。

无论如何,希望有帮助。

如果有人愿意,他们可以移植优秀的 perl 模块 文件类型 到.NET。代码中是针对每种文件类型或正则表达式匹配的一组文件头幻数查找。

这是一个 .NET 文件类型检测库 http://filetypeDetective.codeplex.com/ 但目前它只检测到少量文件。

这个答案是作者答案(Richard Gourlay)的副本,但根据 Rohland 的评论进行了改进,以解决 IIS 8 / win2012 上的问题(其中函数会导致应用程序池崩溃) http://www.pinvoke.net/default.aspx/urlmon.findmimefromdata

using System.Runtime.InteropServices;

...

public static string GetMimeFromFile(string filename)
{

    if (!File.Exists(filename))
        throw new FileNotFoundException(filename + " not found");

    const int maxContent = 256;

    var buffer = new byte[maxContent];
    using (var fs = new FileStream(filename, FileMode.Open))
    {
        if (fs.Length >= maxContent)
            fs.Read(buffer, 0, maxContent);
        else
            fs.Read(buffer, 0, (int) fs.Length);
    }

    var mimeTypePtr = IntPtr.Zero;
    try
    {
        var result = FindMimeFromData(IntPtr.Zero, null, buffer, maxContent, null, 0, out mimeTypePtr, 0);
        if (result != 0)
        {
            Marshal.FreeCoTaskMem(mimeTypePtr);
            throw Marshal.GetExceptionForHR(result);
        }

        var mime = Marshal.PtrToStringUni(mimeTypePtr);
        Marshal.FreeCoTaskMem(mimeTypePtr);
        return mime;
    }
    catch (Exception e)
    {
        if (mimeTypePtr != IntPtr.Zero)
        {
            Marshal.FreeCoTaskMem(mimeTypePtr);
        }
        return "unknown/unknown";
    }
}

[DllImport("urlmon.dll", CharSet = CharSet.Unicode, ExactSpelling = true, SetLastError = false)]
private static extern int FindMimeFromData(IntPtr pBC,
    [MarshalAs(UnmanagedType.LPWStr)] string pwzUrl,
    [MarshalAs(UnmanagedType.LPArray, ArraySubType = UnmanagedType.I1, SizeParamIndex = 3)] byte[] pBuffer,
    int cbSize,
    [MarshalAs(UnmanagedType.LPWStr)] string pwzMimeProposed,
    int dwMimeFlags,
    out IntPtr ppwzMimeOut,
    int dwReserved);

@Steve Morgan 和 @Richard Gourlay 这是一个很好的解决方案,谢谢你们。一个小缺点是,当文件中的字节数为 255 或以下时,mime 类型有时会生成“application/octet-stream”,这对于预期生成“text/plain”的文件来说稍微不准确。我已经更新了您的原始方法来解决这种情况,如下所示:

如果文件中的字节数小于或等于 255 并且推导的 mime 类型为“application/octet-stream”,则创建一个新的字节数组,该数组由重复 n 次的原始文件字节组成,直到总数达到字节数 >= 256。然后重新检查该新字节数组上的 mime 类型。

修改方法:

Imports System.Runtime.InteropServices

<DllImport("urlmon.dll", CharSet:=CharSet.Auto)> _
Private Shared Function FindMimeFromData(pBC As System.UInt32, <MarshalAs(UnmanagedType.LPStr)> pwzUrl As System.String, <MarshalAs(UnmanagedType.LPArray)> pBuffer As Byte(), cbSize As System.UInt32, <MarshalAs(UnmanagedType.LPStr)> pwzMimeProposed As System.String, dwMimeFlags As System.UInt32, _
ByRef ppwzMimeOut As System.UInt32, dwReserverd As System.UInt32) As System.UInt32
End Function
Private Function GetMimeType(ByVal f As FileInfo) As String
    'See http://stackoverflow.com/questions/58510/using-net-how-can-you-find-the-mime-type-of-a-file-based-on-the-file-signature
    Dim returnValue As String = ""
    Dim fileStream As FileStream = Nothing
    Dim fileStreamLength As Long = 0
    Dim fileStreamIsLessThanBByteSize As Boolean = False

    Const byteSize As Integer = 255
    Const bbyteSize As Integer = byteSize + 1

    Const ambiguousMimeType As String = "application/octet-stream"
    Const unknownMimeType As String = "unknown/unknown"

    Dim buffer As Byte() = New Byte(byteSize) {}
    Dim fnGetMimeTypeValue As New Func(Of Byte(), Integer, String)(
        Function(_buffer As Byte(), _bbyteSize As Integer) As String
            Dim _returnValue As String = ""
            Dim mimeType As UInt32 = 0
            FindMimeFromData(0, Nothing, _buffer, _bbyteSize, Nothing, 0, mimeType, 0)
            Dim mimeTypePtr As IntPtr = New IntPtr(mimeType)
            _returnValue = Marshal.PtrToStringUni(mimeTypePtr)
            Marshal.FreeCoTaskMem(mimeTypePtr)
            Return _returnValue
        End Function)

    If (f.Exists()) Then
        Try
            fileStream = New FileStream(f.FullName(), FileMode.Open, FileAccess.Read, FileShare.ReadWrite)
            fileStreamLength = fileStream.Length()

            If (fileStreamLength >= bbyteSize) Then
                fileStream.Read(buffer, 0, bbyteSize)
            Else
                fileStreamIsLessThanBByteSize = True
                fileStream.Read(buffer, 0, CInt(fileStreamLength))
            End If

            returnValue = fnGetMimeTypeValue(buffer, bbyteSize)

            If (returnValue.Equals(ambiguousMimeType, StringComparison.OrdinalIgnoreCase) AndAlso fileStreamIsLessThanBByteSize AndAlso fileStreamLength > 0) Then
                'Duplicate the stream content until the stream length is >= bbyteSize to get a more deterministic mime type analysis.
                Dim currentBuffer As Byte() = buffer.Take(fileStreamLength).ToArray()
                Dim repeatCount As Integer = Math.Floor((bbyteSize / fileStreamLength) + 1)
                Dim bBufferList As List(Of Byte) = New List(Of Byte)
                While (repeatCount > 0)
                    bBufferList.AddRange(currentBuffer)
                    repeatCount -= 1
                End While
                Dim bbuffer As Byte() = bBufferList.Take(bbyteSize).ToArray()
                returnValue = fnGetMimeTypeValue(bbuffer, bbyteSize)
            End If
        Catch ex As Exception
            returnValue = unknownMimeType
        Finally
            If (fileStream IsNot Nothing) Then fileStream.Close()
        End Try
    End If
    Return returnValue
End Function

IIS 7 或更高版本

使用此代码,但您需要成为服务器的管理员

public bool CheckMimeMapExtension(string fileExtension)
        {
            try
            {

                using (
                ServerManager serverManager = new ServerManager())
                {   
                    // connects to default app.config
                    var config = serverManager.GetApplicationHostConfiguration();
                    var staticContent = config.GetSection("system.webServer/staticContent");
                    var mimeMap = staticContent.GetCollection();

                    foreach (var mimeType in mimeMap)
                    {

                        if (((String)mimeType["fileExtension"]).Equals(fileExtension, StringComparison.OrdinalIgnoreCase))
                            return true;

                    }

                }
                return false;
            }
            catch (Exception ex)
            { 
                Console.WriteLine("An exception has occurred: \n{0}", ex.Message);
                Console.Read();
            }

            return false;

        }

当使用 Windows Azure Web 角色或在有限信任中运行您的应用程序的任何其他主机时,请不要忘记您将无法访问注册表或非托管代码。混合方法 - try-catch-for-registry 和内存中字典的组合看起来是一个很好的解决方案,拥有一切。

我使用这段代码来做到这一点:

public class DefaultMimeResolver : IMimeResolver
{
    private readonly IFileRepository _fileRepository;

    public DefaultMimeResolver(IFileRepository fileRepository)
    {
        _fileRepository = fileRepository;
    }

    [DllImport(@"urlmon.dll", CharSet = CharSet.Auto)]
    private static extern System.UInt32 FindMimeFromData(
        System.UInt32 pBC, [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl,
         [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer,
         System.UInt32 cbSize,
         [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed,
         System.UInt32 dwMimeFlags,
         out System.UInt32 ppwzMimeOut,
         System.UInt32 dwReserverd);


    public string GetMimeTypeFromFileExtension(string fileExtension)
    {
        if (string.IsNullOrEmpty(fileExtension))
        {
            throw new ArgumentNullException("fileExtension");
        }

        string mimeType = GetMimeTypeFromList(fileExtension);

        if (String.IsNullOrEmpty(mimeType))
        {
            mimeType = GetMimeTypeFromRegistry(fileExtension);
        }

        return mimeType;
    }

    public string GetMimeTypeFromFile(string filePath)
    {
        if (string.IsNullOrEmpty(filePath))
        {
            throw new ArgumentNullException("filePath");
        }

        if (!File.Exists(filePath))
        {
            throw new FileNotFoundException("File not found : ", filePath);
        }

        string mimeType = GetMimeTypeFromList(Path.GetExtension(filePath).ToLower());

        if (String.IsNullOrEmpty(mimeType))
        {
            mimeType = GetMimeTypeFromRegistry(Path.GetExtension(filePath).ToLower());

            if (String.IsNullOrEmpty(mimeType))
            {
                mimeType = GetMimeTypeFromFileInternal(filePath);
            }
        }

        return mimeType;
    }

    private string GetMimeTypeFromList(string fileExtension)
    {
        string mimeType = null;

        if (fileExtension.StartsWith("."))
        {
            fileExtension = fileExtension.TrimStart('.');
        }

        if (!String.IsNullOrEmpty(fileExtension) && _mimeTypes.ContainsKey(fileExtension))
        {
            mimeType = _mimeTypes[fileExtension];
        }

        return mimeType;
    }

    private string GetMimeTypeFromRegistry(string fileExtension)
    {
        string mimeType = null;
        try
        {
            RegistryKey key = Registry.ClassesRoot.OpenSubKey(fileExtension);

            if (key != null && key.GetValue("Content Type") != null)
            {
                mimeType = key.GetValue("Content Type").ToString();
            }
        }
        catch (Exception)
        {
            // Empty. When this code is running in limited mode accessing registry is not allowed.
        }

        return mimeType;
    }

    private string GetMimeTypeFromFileInternal(string filePath)
    {
        string mimeType = null;

        if (!File.Exists(filePath))
        {
            return null;
        }

        byte[] byteBuffer = new byte[256];

        using (FileStream fileStream = _fileRepository.Get(filePath))
        {
            if (fileStream.Length >= 256)
            {
                fileStream.Read(byteBuffer, 0, 256);
            }
            else
            {
                fileStream.Read(byteBuffer, 0, (int)fileStream.Length);
            }
        }

        try
        {
            UInt32 MimeTypeNum;

            FindMimeFromData(0, null, byteBuffer, 256, null, 0, out MimeTypeNum, 0);

            IntPtr mimeTypePtr = new IntPtr(MimeTypeNum);
            string mimeTypeFromFile = Marshal.PtrToStringUni(mimeTypePtr);

            Marshal.FreeCoTaskMem(mimeTypePtr);

            if (!String.IsNullOrEmpty(mimeTypeFromFile) && mimeTypeFromFile != "text/plain" && mimeTypeFromFile != "application/octet-stream")
            {
                mimeType = mimeTypeFromFile;
            }
        }
        catch
        {
            // Empty. 
        }

        return mimeType;
    }

    private readonly Dictionary<string, string> _mimeTypes = new Dictionary<string, string>
        {
            {"ai", "application/postscript"},
            {"aif", "audio/x-aiff"},
            {"aifc", "audio/x-aiff"},
            {"aiff", "audio/x-aiff"},
            {"asc", "text/plain"},
            {"atom", "application/atom+xml"},
            {"au", "audio/basic"},
            {"avi", "video/x-msvideo"},
            {"bcpio", "application/x-bcpio"},
            {"bin", "application/octet-stream"},
            {"bmp", "image/bmp"},
            {"cdf", "application/x-netcdf"},
            {"cgm", "image/cgm"},
            {"class", "application/octet-stream"},
            {"cpio", "application/x-cpio"},
            {"cpt", "application/mac-compactpro"},
            {"csh", "application/x-csh"},
            {"css", "text/css"},
            {"dcr", "application/x-director"},
            {"dif", "video/x-dv"},
            {"dir", "application/x-director"},
            {"djv", "image/vnd.djvu"},
            {"djvu", "image/vnd.djvu"},
            {"dll", "application/octet-stream"},
            {"dmg", "application/octet-stream"},
            {"dms", "application/octet-stream"},
            {"doc", "application/msword"},
            {"docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document"},
            {"dotx", "application/vnd.openxmlformats-officedocument.wordprocessingml.template"},
            {"docm", "application/vnd.ms-word.document.macroEnabled.12"},
            {"dotm", "application/vnd.ms-word.template.macroEnabled.12"},
            {"dtd", "application/xml-dtd"},
            {"dv", "video/x-dv"},
            {"dvi", "application/x-dvi"},
            {"dxr", "application/x-director"},
            {"eps", "application/postscript"},
            {"etx", "text/x-setext"},
            {"exe", "application/octet-stream"},
            {"ez", "application/andrew-inset"},
            {"gif", "image/gif"},
            {"gram", "application/srgs"},
            {"grxml", "application/srgs+xml"},
            {"gtar", "application/x-gtar"},
            {"hdf", "application/x-hdf"},
            {"hqx", "application/mac-binhex40"},
            {"htc", "text/x-component"},
            {"htm", "text/html"},
            {"html", "text/html"},
            {"ice", "x-conference/x-cooltalk"},
            {"ico", "image/x-icon"},
            {"ics", "text/calendar"},
            {"ief", "image/ief"},
            {"ifb", "text/calendar"},
            {"iges", "model/iges"},
            {"igs", "model/iges"},
            {"jnlp", "application/x-java-jnlp-file"},
            {"jp2", "image/jp2"},
            {"jpe", "image/jpeg"},
            {"jpeg", "image/jpeg"},
            {"jpg", "image/jpeg"},
            {"js", "application/x-javascript"},
            {"kar", "audio/midi"},
            {"latex", "application/x-latex"},
            {"lha", "application/octet-stream"},
            {"lzh", "application/octet-stream"},
            {"m3u", "audio/x-mpegurl"},
            {"m4a", "audio/mp4a-latm"},
            {"m4b", "audio/mp4a-latm"},
            {"m4p", "audio/mp4a-latm"},
            {"m4u", "video/vnd.mpegurl"},
            {"m4v", "video/x-m4v"},
            {"mac", "image/x-macpaint"},
            {"man", "application/x-troff-man"},
            {"mathml", "application/mathml+xml"},
            {"me", "application/x-troff-me"},
            {"mesh", "model/mesh"},
            {"mid", "audio/midi"},
            {"midi", "audio/midi"},
            {"mif", "application/vnd.mif"},
            {"mov", "video/quicktime"},
            {"movie", "video/x-sgi-movie"},
            {"mp2", "audio/mpeg"},
            {"mp3", "audio/mpeg"},
            {"mp4", "video/mp4"},
            {"mpe", "video/mpeg"},
            {"mpeg", "video/mpeg"},
            {"mpg", "video/mpeg"},
            {"mpga", "audio/mpeg"},
            {"ms", "application/x-troff-ms"},
            {"msh", "model/mesh"},
            {"mxu", "video/vnd.mpegurl"},
            {"nc", "application/x-netcdf"},
            {"oda", "application/oda"},
            {"ogg", "application/ogg"},
            {"pbm", "image/x-portable-bitmap"},
            {"pct", "image/pict"},
            {"pdb", "chemical/x-pdb"},
            {"pdf", "application/pdf"},
            {"pgm", "image/x-portable-graymap"},
            {"pgn", "application/x-chess-pgn"},
            {"pic", "image/pict"},
            {"pict", "image/pict"},
            {"png", "image/png"},
            {"pnm", "image/x-portable-anymap"},
            {"pnt", "image/x-macpaint"},
            {"pntg", "image/x-macpaint"},
            {"ppm", "image/x-portable-pixmap"},
            {"ppt", "application/vnd.ms-powerpoint"},
            {"pptx", "application/vnd.openxmlformats-officedocument.presentationml.presentation"},
            {"potx", "application/vnd.openxmlformats-officedocument.presentationml.template"},
            {"ppsx", "application/vnd.openxmlformats-officedocument.presentationml.slideshow"},
            {"ppam", "application/vnd.ms-powerpoint.addin.macroEnabled.12"},
            {"pptm", "application/vnd.ms-powerpoint.presentation.macroEnabled.12"},
            {"potm", "application/vnd.ms-powerpoint.template.macroEnabled.12"},
            {"ppsm", "application/vnd.ms-powerpoint.slideshow.macroEnabled.12"},
            {"ps", "application/postscript"},
            {"qt", "video/quicktime"},
            {"qti", "image/x-quicktime"},
            {"qtif", "image/x-quicktime"},
            {"ra", "audio/x-pn-realaudio"},
            {"ram", "audio/x-pn-realaudio"},
            {"ras", "image/x-cmu-raster"},
            {"rdf", "application/rdf+xml"},
            {"rgb", "image/x-rgb"},
            {"rm", "application/vnd.rn-realmedia"},
            {"roff", "application/x-troff"},
            {"rtf", "text/rtf"},
            {"rtx", "text/richtext"},
            {"sgm", "text/sgml"},
            {"sgml", "text/sgml"},
            {"sh", "application/x-sh"},
            {"shar", "application/x-shar"},
            {"silo", "model/mesh"},
            {"sit", "application/x-stuffit"},
            {"skd", "application/x-koan"},
            {"skm", "application/x-koan"},
            {"skp", "application/x-koan"},
            {"skt", "application/x-koan"},
            {"smi", "application/smil"},
            {"smil", "application/smil"},
            {"snd", "audio/basic"},
            {"so", "application/octet-stream"},
            {"spl", "application/x-futuresplash"},
            {"src", "application/x-wais-source"},
            {"sv4cpio", "application/x-sv4cpio"},
            {"sv4crc", "application/x-sv4crc"},
            {"svg", "image/svg+xml"},
            {"swf", "application/x-shockwave-flash"},
            {"t", "application/x-troff"},
            {"tar", "application/x-tar"},
            {"tcl", "application/x-tcl"},
            {"tex", "application/x-tex"},
            {"texi", "application/x-texinfo"},
            {"texinfo", "application/x-texinfo"},
            {"tif", "image/tiff"},
            {"tiff", "image/tiff"},
            {"tr", "application/x-troff"},
            {"tsv", "text/tab-separated-values"},
            {"txt", "text/plain"},
            {"ustar", "application/x-ustar"},
            {"vcd", "application/x-cdlink"},
            {"vrml", "model/vrml"},
            {"vxml", "application/voicexml+xml"},
            {"wav", "audio/x-wav"},
            {"wbmp", "image/vnd.wap.wbmp"},
            {"wbmxl", "application/vnd.wap.wbxml"},
            {"wml", "text/vnd.wap.wml"},
            {"wmlc", "application/vnd.wap.wmlc"},
            {"wmls", "text/vnd.wap.wmlscript"},
            {"wmlsc", "application/vnd.wap.wmlscriptc"},
            {"wrl", "model/vrml"},
            {"xbm", "image/x-xbitmap"},
            {"xht", "application/xhtml+xml"},
            {"xhtml", "application/xhtml+xml"},
            {"xls", "application/vnd.ms-excel"},
            {"xml", "application/xml"},
            {"xpm", "image/x-xpixmap"},
            {"xsl", "application/xml"},
            {"xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"},
            {"xltx", "application/vnd.openxmlformats-officedocument.spreadsheetml.template"},
            {"xlsm", "application/vnd.ms-excel.sheet.macroEnabled.12"},
            {"xltm", "application/vnd.ms-excel.template.macroEnabled.12"},
            {"xlam", "application/vnd.ms-excel.addin.macroEnabled.12"},
            {"xlsb", "application/vnd.ms-excel.sheet.binary.macroEnabled.12"},
            {"xslt", "application/xslt+xml"},
            {"xul", "application/vnd.mozilla.xul+xml"},
            {"xwd", "image/x-xwindowdump"},
            {"xyz", "chemical/x-xyz"},
            {"zip", "application/zip"}
        };
}

我最终使用了 Netomatix 的 Winista MimeDetector。创建帐户后可以免费下载源代码: http://www.netomatix.com/Products/DocumentManagement/MimeDetector.aspx

MimeTypes g_MimeTypes = new MimeTypes("mime-types.xml");
sbyte [] fileData = null;

using (System.IO.FileStream srcFile = new System.IO.FileStream(strFile, System.IO.FileMode.Open))
{
    byte [] data = new byte[srcFile.Length];
    srcFile.Read(data, 0, (Int32)srcFile.Length);
    fileData = Winista.Mime.SupportUtil.ToSByteArray(data);
}

MimeType oMimeType = g_MimeTypes.GetMimeType(fileData);

这是此处回答的另一个问题的一部分: Urlmon.dll 中 FindMimeFromData 方法的替代方法,该方法具有更多 MIME 类型我认为这个问题的最佳解决方案。

Winista MIME 检测与 URLMon 在这里下载项目:https://github.com/MeaningOfLights/MimeDetect

假设有人用 jpg 扩展名重命名了 exe,您仍然可以使用二进制分析来确定“真实”文件格式。它不检测 swf 或 flv,但几乎可以检测所有其他众所周知的格式 + 您可以获得十六进制编辑器并添加它可以检测到的更多文件。

文件魔法

Winista 使用 XML 文件“mime-type.xml”检测真实的 MIME 类型,该文件包含有关文件类型的信息以及用于识别内容类型的签名。例如:

<!--
 !   Audio primary type
 ! -->

<mime-type name="audio/basic"
           description="uLaw/AU Audio File">
    <ext>au</ext><ext>snd</ext>
    <magic offset="0" type="byte" value="2e736e64000000"/>
</mime-type>

<mime-type name="audio/midi"
           description="Musical Instrument Digital Interface MIDI-sequention Sound">
    <ext>mid</ext><ext>midi</ext><ext>kar</ext>
    <magic offset="0" value="MThd"/>
</mime-type>

<mime-type name="audio/mpeg"
           description="MPEG Audio Stream, Layer III">
    <ext>mp3</ext><ext>mp2</ext><ext>mpga</ext>
    <magic offset="0" value="ID3"/>
</mime-type>

当 Winista 无法检测到真正的文件格式时,我又求助于 URLMon 方法:

public class urlmonMimeDetect
{
    [DllImport(@"urlmon.dll", CharSet = CharSet.Auto)]
    private extern static System.UInt32 FindMimeFromData(
        System.UInt32 pBC,
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl,
        [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer,
        System.UInt32 cbSize,
        [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed,
        System.UInt32 dwMimeFlags,
        out System.UInt32 ppwzMimeOut,
        System.UInt32 dwReserverd
    );

public string GetMimeFromFile(string filename)
{
    if (!File.Exists(filename))
        throw new FileNotFoundException(filename + " not found");

    byte[] buffer = new byte[256];
    using (FileStream fs = new FileStream(filename, FileMode.Open, FileAccess.Read))
    {
        if (fs.Length >= 256)
            fs.Read(buffer, 0, 256);
        else
            fs.Read(buffer, 0, (int)fs.Length);
    }
    try
    {
        System.UInt32 mimetype;
        FindMimeFromData(0, null, buffer, 256, null, 0, out mimetype, 0);
        System.IntPtr mimeTypePtr = new IntPtr(mimetype);
        string mime = Marshal.PtrToStringUni(mimeTypePtr);
        Marshal.FreeCoTaskMem(mimeTypePtr);
        return mime;
    }
    catch (Exception e)
    {
        return "unknown/unknown";
    }
}
}

从 Winista 方法内部,我在这里求助于 URLMon:

   public MimeType GetMimeTypeFromFile(string filePath)
    {
        sbyte[] fileData = null;
        using (FileStream srcFile = new FileStream(filePath, FileMode.Open, FileAccess.Read))
        {
            byte[] data = new byte[srcFile.Length];
            srcFile.Read(data, 0, (Int32)srcFile.Length);
            fileData = Winista.Mime.SupportUtil.ToSByteArray(data);
        }

        MimeType oMimeType = GetMimeType(fileData);
        if (oMimeType != null) return oMimeType;

        //We haven't found the file using Magic (eg a text/plain file)
        //so instead use URLMon to try and get the files format
        Winista.MimeDetect.URLMONMimeDetect.urlmonMimeDetect urlmonMimeDetect = new Winista.MimeDetect.URLMONMimeDetect.urlmonMimeDetect();
        string urlmonMimeType = urlmonMimeDetect.GetMimeFromFile(filePath);
        if (!string.IsNullOrEmpty(urlmonMimeType))
        {
            foreach (MimeType mimeType in types)
            {
                if (mimeType.Name == urlmonMimeType)
                {
                    return mimeType;
                }
            }
        }

        return oMimeType;
    }
许可以下: CC-BY-SA归因
不隶属于 StackOverflow
scroll top