Csharp调用微软COM转换word为HTML

             使用微软的office中的word软件只要使用另存为就可以把一个word保存为HTML网页文件。但如何通过程序调用完成转化呢？

以下使用office 2007为例，其他版本略有不同。

  1添加引用，对于不同的版本，有所不一样。当然前提自然是安装了对应的微软office软件。

2转换代码如下：

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using Word=Microsoft.Office.Interop.Word;  
namespace CommonConvert
{
    public class WordToHtml
    {
        /// <summary>
        /// 使用反射调用方法,返回生成的HTML文件路径
        /// </summary>
        /// <param name="wordFullFileName"></param>
        /// <returns></returns>
        public string WordToHtmlFile(string wordFullFileName)
        {
            //在此处放置用户代码以初始化页面 
            Word.Application word = new Word.Application();
            Type wordType = word.GetType();
            Word.Documents docs = word.Documents;
            //打开文件 
            Type docsType = docs.GetType();
            Word.Document doc = (Word.Document)docsType.InvokeMember("Open", System.Reflection.BindingFlags.InvokeMethod, null, docs, new Object[] { wordFullFileName, true, true });
                    
            Type docType = doc.GetType();          
           string htmlFullFileName = wordFullFileName + ".html"; //HTML文件路径          
            //转换格式，另存为  
            docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod, null, doc, new object[] { htmlFullFileName, Word.WdSaveFormat.wdFormatFilteredHTML });
            docType.InvokeMember("Close", System.Reflection.BindingFlags.InvokeMethod, null, doc, null);
            //退出 Word 
            wordType.InvokeMember("Quit", System.Reflection.BindingFlags.InvokeMethod, null, word, null);
            return htmlFullFileName;
        }
        /// <summary>
        /// 直接调用方法，不使用反射
        /// </summary>
        /// <param name="wordFullFileName"></param>
        /// <returns></returns>
        public string WordToHtmlFile2(string wordFullFileName)
        {
            //在此处放置用户代码以初始化页面 
            Word.Application word = new Word.Application();          
            Word.Documents docs = word.Documents;
            //打开文件 
           // Type docsType = docs.GetType();
            //Word.Document doc = (Word.Document)docsType.InvokeMember("Open", System.Reflection.BindingFlags.InvokeMethod, null, docs, new Object[] { wordFullFileName, true, true });
            object owordFullFileName = wordFullFileName;
            Word.Document doc = docs.Open(ref owordFullFileName);           
            //转换格式，另存为 
            string htmlFullFileName = wordFullFileName + ".html"; //HTML文件路径             
            doc.SaveAs(htmlFullFileName, Word.WdSaveFormat.wdFormatFilteredHTML);  
            doc.Close();
            //退出 Word 
            word.Quit();
            return htmlFullFileName.ToString();
        }
    }
}

参考文章