将页面内容转换Pdf\Word\Excel格式

项目中用到了将邮件内容转换为Pdf、Word、Excel格式，做为邮件附件发送。

查了一些解决方案，走了一些弯路。以此代码记录下。

转换PDF需要下载NReco.PdfGenerator.dll

以下是相关代码。

 /// <summary>
 /// 格式转换
 /// </summary>
 /// <param name="content">邮件内容</param>
 /// <param name="fileType">转换类型</param>
 /// <returns></returns>
 private static Byte[] ChangeContent(string content, string fileType)
 {

     Byte[] fileSteream = null;
     try
     {

         // 定义正则表达式用来匹配 img 标签
         Regex regImg = new Regex(@"<img\b[^<>]*?\bmarktype=[""'][^<>]*>", RegexOptions.IgnoreCase);
         Regex regImgMarktype = new Regex(@"\bsrc=[""'](?<src>[^\s\t\r\n""'<>]*)[^<>]*", RegexOptions.IgnoreCase);
         MatchCollection matches = regImg.Matches(content);

         // 取得匹配项列表
         foreach (Match match in matches)
         {
             string srcUrl = "";
             if (match.Value != null)
             {
                 MatchCollection matchesMarktype = regImgMarktype.Matches(match.Value);
                 foreach (Match mat in matchesMarktype)
                 {
                     var src = mat.Groups["src"].Value;
                     if (!string.IsNullOrEmpty(src))
                     {
                         srcUrl = ServerCommon.SharedDirc + src; //替换图片路径
                         content = content.Replace(src, srcUrl);
                     }
                 }
             }
         }

         switch (fileType.ToUpper())
         {
             case "PDF":
                 fileSteream = ConversionFormat.HtmlToPDF(content);
                 break;
             case "WORD":
                 fileSteream = ConversionFormat.HtmlToWrod(content);
                 break;
             case "EXCEL":
                 fileSteream = ConversionFormat.HtmlToExcel(content);
                 break;
             default:
                 break;
         }
     }
     catch (Exception ex)
     {
          //log
     }

     return fileSteream;
 }    

 /// <summary>
 /// 输出内容格式转换
 /// </summary>
 public class ConversionFormat
 {
     public static byte[] HtmlToPDF(string content)
     {
         var meat = "<meta http-equiv='Content-Type' content='text/html; charset=utf-8'>";//解决PDF乱码问题
         var htmlContent = meat + content;
         var htmlToPdf = new NReco.PdfGenerator.HtmlToPdfConverter();
         var pdfBytes = htmlToPdf.GeneratePdf(htmlContent);

         return pdfBytes;
     }

     public static byte[] HtmlToWrod(string content)
     {
         //获得字节数组
         byte[] data = new UTF8Encoding().GetBytes(content);

         return data;
     }

     public static byte[] HtmlToExcel(string content)
     {
         //获得字节数组
         byte[] data = new UTF8Encoding().GetBytes(content);

         return data;
     }
 }

简单测试下,添加一个保存文件的方法,就能看到效果了。

 public void SaveFile(string fileName, byte[] Bytes)
         {
             string filePath = @"D:\temp\" + fileName;
             if (!(Directory.Exists(@"D:\temp")))
             {
                 Directory.CreateDirectory(@"D:\temp");
             }
             if (File.Exists(filePath))
             {
                 return;
             }

             FileStream fs = new FileStream(filePath, FileMode.Create);
             //获得字节数组
             //byte[] data = new UTF8Encoding().GetBytes(pdfBytes);
             //开始写入
             fs.Write(Bytes, , Bytes.Length);
             //清空缓冲区、关闭流
             fs.Flush();
             fs.Close();
         }