C# web实现word 转Html、office转Html、pdf转图片 在线预览文件

 改篇 pdf 预览再本机没问题，发布再iis中 不行 ，（使用剪贴板的问题..excel和word 可以,）

pdf解决：请看我的博文 ----最终解决篇

详细配置及代码

word 转Html

 1 /// <summary> 
 2         /// word转成html 
 3         /// </summary> 
 4         /// <param name="wordFileName"></param> 
 5         private void WordToHtml(object wordFileName,string htmlWord)
 6         {
 7             //在此处放置用户代码以初始化页面 
 8             Word.ApplicationClass word = new Word.ApplicationClass();
 9             Type wordType = word.GetType();
10             Word.Documents docs = word.Documents;
11             //打开文件 
12             Type docsType = docs.GetType();
13             Word.Document doc = (Word.Document)docsType.InvokeMember("Open", System.Reflection.BindingFlags.InvokeMethod, null, docs, new Object[] { wordFileName, true, true });
14             //转换格式，另存为 
15             string a = doc.Comments.ToString();
16             Type docType = doc.GetType();
17             string wordSaveFileName = wordFileName.ToString();
18 
19       
20 
21            string strSaveFileName = htmlWord + "\\" + Path.GetFileNameWithoutExtension(wordSaveFileName) + ".html";
22 
23             object saveFileName = (object)strSaveFileName;
24             docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod, null, doc, new object[] { saveFileName, Word.WdSaveFormat.wdFormatFilteredHTML });
25             docType.InvokeMember("Close", System.Reflection.BindingFlags.InvokeMethod, null, doc, null);
26             //退出 Word 
27             wordType.InvokeMember("Quit", System.Reflection.BindingFlags.InvokeMethod, null, word, null);
28             
29         } 

引入  Microsoft.Office.Interop.Word;

office转Html

/// <summary> 
        /// Excel转成html 
        /// </summary> 
        public void ReadExcel(string rFilePath, string rHtmlFilePath)
        {
            Excel.Application repExcel = new Excel.Application();
            Excel.Workbook workbook = null;

            //xlsFile为Excel文件路径   
            workbook = repExcel.Application.Workbooks.Open(rFilePath,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value);

            //htmlFile   是要另存的html文件名   

            object ofmt = Excel.XlFileFormat.xlHtml;
            workbook.SaveAs(rHtmlFilePath,
             ofmt,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Excel.XlSaveAsAccessMode.xlNoChange,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value,
             Missing.Value);

            object osave = false;
            workbook.Close(osave, Missing.Value, Missing.Value);

        }

引入Microsoft.Office.Interop.Excel;

pdf  转图片

说明：本方法 用  acrobat 的官方接口  

需要安装  acrobat   professional  8.0或更高版本

然后再vs中添加com组件  abode  acrobat  版本号   type  library  只有安装了上面软件 才回有

在web页 头部 添加   AspCompat="true"    控制台程序 要在main函数上加  [STAThread]  保证单线程模型下 才能访问 剪贴板

using System.IO;
using System.Reflection;
using DataHelp;
using System.Text;
using System.Drawing.Imaging;
using System.Windows.Forms;
using System.Drawing;
using System.Runtime.InteropServices;

  /// <summary>
        /// Pdf导图片
        /// </summary>
        /// <param name="pdfInputPathDirectory"></param>
        /// <param name="pngOutputPath"></param>
        /// <param name="format"></param>
        /// <returns></returns>
        
        public string PDFToPic(string pdfInputPathDirectory, string pngOutputPath, ImageFormat format)
        {
            StringBuilder b = new StringBuilder();
            ImageFormat formate = format;
            // Acrobat objects
            Acrobat.CAcroPDDoc pdfDoc = null;
            Acrobat.CAcroPDPage pdfPage = null;
            Acrobat.CAcroRect pdfRect = null;
            Acrobat.CAcroPoint pdfPoint = null;
            try
            {
                string[] files = new string[] { pdfInputPathDirectory };
                string dic = Path.GetDirectoryName(pdfInputPathDirectory);
                //string[] files = Directory.GetFiles(dic, "*.pdf");
                for (int n = 0; n < files.Length; n++)
                {
                    string inputFile = files[n].ToString();
                    string fileName = files[n].Substring(files[n].LastIndexOf(@"\") + 1).Replace(".pdf", "");
                    // Will always be available as .NET framework ships with all
                    pdfDoc = (Acrobat.CAcroPDDoc)Microsoft.VisualBasic.Interaction.CreateObject("AcroExch.PDDoc", "");
                    bool ret = pdfDoc.Open(inputFile);
                    if (!ret)
                    {
                        throw new FileNotFoundException();
                    }
                    else
                    {

                        b = b.AppendLine("<span>pdfDoc成功打开文件！！！</span>");
                    }
                    // Get the number of pages (to be used later if you wanted to store that information)
                    int pageCount = pdfDoc.GetNumPages();
                    b = b.AppendLine("<ul style='azimuth:center; list-style-type:none;' >");


                    for (int i = 0; i < pageCount; i++)
                    {
                        // Get the first page
                        pdfPage = (Acrobat.CAcroPDPage)pdfDoc.AcquirePage(i);

                        pdfPoint = (Acrobat.CAcroPoint)pdfPage.GetSize();
                        b = b.AppendLine("<li>  <span>pdfPoint.x=" + pdfPoint.x + ";pdfPoint.y=" + pdfPoint.y + "</span>   </li>");
                        pdfRect = (Acrobat.CAcroRect)Microsoft.VisualBasic.Interaction.CreateObject("AcroExch.Rect", "");
                        pdfRect.Left = 0;
                        pdfRect.right = pdfPoint.x;
                        pdfRect.Top = 0;
                        pdfRect.bottom = pdfPoint.y;
                        // Render to clipboard, scaled by 100 percent (ie. original size)
                        // Even though we want a smaller image, better for us to scale in .NET
                        // than Acrobat as it would greek out small text
                        // see http://www.adobe.com/support/techdocs/1dd72.htm
                        //清空剪贴板
                        //Clipboard.Clear();
                       //b = b.AppendLine("<li>  <span>Clipboard.Clear();清空剪贴板 </span>   </li>");

                       pdfPage.CopyToClipboard(pdfRect, 0, 0, 100);

                        //b = b.AppendLine("<li>  <span>pdfPage.CopyToClipboard(pdfRect, 0, 0, 100)=" +pdfPage.CopyToClipboard(pdfRect, 0, 0, 100)+ ";复制到剪贴板</span>   </li>");


                        System.Windows.Forms.IDataObject clipboardData = Clipboard.GetDataObject();
                        bool c = false;
                        if (clipboardData!=null )
                        {
                            c = true;
                        }


                        b = b.AppendLine("<li>  <span> Clipboard.GetDataObject()=" + c + "剪贴板中是否有数据;</span>   </li>");



                       b = b.AppendLine("<li>  <span>clipboardData.GetDataPresent(DataFormats.Bitmap)=" + clipboardData.GetDataPresent(DataFormats.Bitmap) + ";</span>   </li>");

                        if (clipboardData.GetDataPresent(DataFormats.Bitmap))
                        {
                            Bitmap pdfBitmap = (Bitmap)clipboardData.GetData(DataFormats.Bitmap);

                            b = b.AppendLine("<li>  <span>生成图片的大小： pdfBitmap.Size.Height=" + pdfBitmap.Size.Height + "; pdfBitmap.Size.Width=" + pdfBitmap.Size.Width + "</span>   </li>");


                           
                            string dPath = Path.Combine(pngOutputPath, i.ToString("0000") + "." + formate.ToString());

                            b = b.AppendLine("<li>  <span>生成图片的路径：" + dPath + ";</span>   </li>");


                            pdfBitmap.Save(
                           dPath, formate);
                            pdfBitmap.Dispose();
                        }
                        b = b.AppendLine("<li>  <img src='..\\" + imgDire + "\\" + i.ToString("0000") + "." + formate.ToString() + "'  />       </li><span>第" + (i + 1) + "页</span>");
                    }

                    pdfDoc.Close();
                    // Not sure how why it is to do this, but Acrobat is not the best behaved COM object
                    // see http://blogs.msdn.com/yvesdolc/archive/2004/04/17/115379.aspx
                    Marshal.ReleaseComObject(pdfPage);
                    Marshal.ReleaseComObject(pdfRect);
                    Marshal.ReleaseComObject(pdfDoc);
                }
                b = b.AppendLine("</ul>");
            }
            catch (System.Exception ex)
            {
                Response.Write(ex.ToString());
            }
            return b.ToString();
        }

关于发布：

offic 组件发布问题

 我的服务器环境是 windows servers 2008 64位操作系统

1、  在服务器上安装Office的Excel相关软件（推荐安装Office 2007）；

2、  Cmd中输入命令 comexp.msc -32  启动组件服务（启动组件服务 方法  运行 mmc、mmc -32(32) 、DCOMCNFG.exe(64)） 不行一个一个

3、  依次双击"组件服务"->"计算机"->"我的电脑"->"DCOM配置"；

4、  在"DCOM配置"中找到"Microsoft Excel Application",在它上面点击右键,然后点击"属性",弹出"Microsoft Excel应用程序属性"对话框；

5、  点击"标识"标签,选择 启动用户（默认选项） ；

6、  点击"安全"标签,在以下  三个项目中都选中   “自定义”  添加 ”everyone”  并分配最大权限（全选）

7、设置Web.config文件   在Web.config文件的<system.web>中加入<identity impersonate="true"/>  （没有这一步 会报Excel进程无法打开相应的excel文件）。

Ok了

Word 配置同上。

关于pdf 发布：   需要在 服务器上安装 上诉软件

     我在本机vs 和服务器vs中 测试没问题  ，发布到iis中  无法取到 剪贴板中的数据    也不报错     iis中应用程序池 的权限我也设置到最大  ，依然无果。

还是这种 iis中访问剪贴板的 方法 违反 安全性 或剪贴板只能在单线程模型下访问  与这个相悖 ？？？？？？？？？？？？？？？？

欢迎留言探讨》》》》》