关于　c#把word文档转换成html后取出html文件中的内容的问题【中国IT软件知识库...

有人通过下面这种方法将word转为html，

private void Page_Load(object sender, System.EventArgs e)
 {
  // 在此处放置用户代码以初始化页面
    Word.ApplicationClass word = new Word.ApplicationClass();
    Type wordType = word.GetType();
    Word.Documents docs = word.Documents;

    // 打开文件
    Type docsType = docs.GetType();
    object fileName = "d:\\tmp\\aaa.doc";
    Word.Document doc = (Word.Document)docsType.InvokeMember("Open",
    System.Reflection.BindingFlags.InvokeMethod, null, docs, new Object[] {fileName, true, true});
         
    // 转换格式，另存为
    Type docType = doc.GetType();
    object saveFileName = "d:\\tmp\\aaa.html";
    //下面是Microsoft Word 9 Object Library的写法，如果是10，可能写成：
    //docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod,
     null, doc, new object[]{saveFileName, Word.WdSaveFormat.wdFormatFilteredHTML});
    ///其它格式：
    ///wdFormatHTML
    ///wdFormatDocument
    ///wdFormatDOSText
    ///wdFormatDOSTextLineBreaks
    ///wdFormatEncodedText
    ///wdFormatRTF
    ///wdFormatTemplate
    ///wdFormatText
    ///wdFormatTextLineBreaks
    ///wdFormatUnicodeText
    docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod,
     null, doc, new object[]{saveFileName, Word.WdSaveFormat.wdFormatHTML});

    // 退出 Word
    wordType.InvokeMember("Quit", System.Reflection.BindingFlags.InvokeMethod,
     null, word, null);
}