package com.wiseweb.util; import com.jacob.activeX.ActiveXComponent; import com.jacob.com.Dispatch; import com.jacob.com.Variant; public class WordtoHtml { //------------------------------------------------------------------------------ //方法原型: change(String paths) //功能描述: 将指定目录下面所有的doc文件转化为HTML并存储在相同目录下 //输入参数: String //输出参数: 无 //返 回 值: 无 //其它说明: 递归 //------------------------------------------------------------------------------ public static boolean change (String FolderPath,String FileName){ String FileFormat = ""; System.out.println(FolderPath); FileFormat = FileName.substring(FileName.length()-4,FileName.length()); System.out.println(FileFormat); if(FileFormat.equalsIgnoreCase(".doc")) { String DocFile = FolderPath +"//"+ FileName; System.out.println("word文件路径:"+DocFile); //word文件的完整路径 String HtmlFile = DocFile.substring(0, (DocFile.length() - 4)) + ".html"; System.out.println("htm文件路径:"+HtmlFile); //html文件的完整路径 ActiveXComponent app = new ActiveXComponent("Word.Application"); //启动word try { app.setProperty("Visible", new Variant(false)); //设置word程序非可视化运行 Dispatch docs = app.getProperty("Documents").toDispatch(); Dispatch doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{DocFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch(); //打开word文件 Dispatch.invoke(doc,"SaveAs",Dispatch.Method, new Object[]{HtmlFile,new Variant(8)}, new int[1]); //作为htm格式保存文件 Dispatch.call(doc, "Close",new Variant(false)); //关闭文件 } catch (Exception e) { e.printStackTrace(); } finally { app.invoke("Quit", new Variant[] {}); //退出word程序 } //转化完毕 return true; } return false; } //------------------------------------------------------------------------------ //方法原型: main(String[] args) //功能描述: main文件 //输入参数: 无 //输出参数: 无 //返 回 值: 无 //其它说明: 无 //------------------------------------------------------------------------------ public static void main(String[] args) { // String paths = new String("E://wordToHtml"); String paths = new String("E:"); // String filename = "a.doc"; String filename = "servlet和jsp学习指南(Budi kurniawan).doc"; change(paths, filename); } }其实原理就是利用word把文档打开,然后另存为html格式就ok了。
原文:http://blog.csdn.net/benjamin_whx/article/details/38851517