将Word文档转化为HTML格式的文档
利用Word.Application提供的方法,可以很轻易地将Word文档转化为HTML等其它格式,下面就是实现的全部的代码:
Visual C#
WordToHtml.aspx
<%@ Page language="c#" Codebehind="WordToHtml.aspx.cs" AutoEventWireup="false"
Inherits="aspxWebcs.WordToHtml" %>
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" >
<HTML>
<HEAD>
<title>WordToHtml</title>
<meta name="GENERATOR" Content="Microsoft Visual Studio .NET 7.1">
<meta name="CODE_LANGUAGE" Content="C#">
<meta name="vs_defaultClientScript" content="JavaScript">
<meta name="vs_targetSchema" content="http://schemas.microsoft.com/intellisense/ie5">
</HEAD>
<body MS_POSITIONING="GridLayout">
<form id="Form1" method="post" runat="server">
</form>
</body>
</HTML>
WordToHtml.aspx.cs
using System;
using System.Collections;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Web;
using System.Web.SessionState;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.HtmlControls;
using Office;
namespace aspxWebcs
{
/// <summary>
/// WordToHtml 的摘要说明。
/// 首先要添加引用:Microsoft Word 9.0 Object Library
/// </summary>
public class WordToHtml : System.Web.UI.Page
{
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