POI遍历文件夹读取word文档

package com;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.LinkedList;

import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.xmlbeans.XmlException;

import com.jacob.activeX.ActiveXComponent;
import com.jacob.com.Dispatch;
import com.jacob.com.Variant;

public class Test {

	public static String fileToRead2007 = "f:/tt.docx";
	public static String fileToRead2003 = "f:/spring2.5 学习笔记.doc";
	public static final int WORD_HTML = 8;
	private static ArrayList filelist = new ArrayList();
//	private static LinkedList filelist = new LinkedList();

	public static void main(String[] args) throws Exception {
		// 创建输入流读取DOC文件
		long a = System.currentTimeMillis();
		refreshFileList("f:\\word");

		for (int i = 0; i < filelist.size(); i++) {
			// 取得文件类型 2003
			//					System.out.println("filelist:"+filelist.get(i).toString());
			if (filelist.get(i).toString().substring(
					filelist.get(i).toString().length() - 3,
					filelist.get(i).toString().length()).equals("doc")) {
				System.out.println("filelist:" + filelist.get(i).toString());
				FileInputStream in = new FileInputStream(filelist.get(i)
						.toString());
				String wordText2003 = Test.extractTextFromDOC(in);
				System.out.println("wordText2003=======" + wordText2003);
			} else if (filelist.get(i).toString().substring(
					filelist.get(i).toString().length() - 4,
					filelist.get(i).toString().length()).equals("docx")) {
				System.out.println("filelist:" + filelist.get(i).toString());
				String wordText2007 = Test.extractTextFromDOC2007(filelist.get(
						i).toString());
				System.out.println("wordText2007=======" + wordText2007);
			}

		}
		System.out.println(System.currentTimeMillis() - a);
	}

	public static void wordToHtml(String docfile, String htmlfile) {
		ActiveXComponent app = new ActiveXComponent("Word.Application"); // 启动word 

		try {
			app.setProperty("Visible", new Variant(false));
			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();
			Dispatch.invoke(doc, "SaveAs", Dispatch.Method, new Object[] {
					htmlfile, new Variant(WORD_HTML) }, new int[1]);
			Variant f = new Variant(false);
			Dispatch.call(doc, "Close", f);

		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			app.invoke("Quit", new Variant[] {});
		}

	}

	/**
	 * jacob word转html
	 * @param paths
	 * @param savepaths
	 */
	public static void change(String paths, String savepaths) {

		File d = new File(paths);
		System.out.println("d:" + d);
		// 取得当前文件夹下所有文件和目录的列表
		File lists[] = d.listFiles();
		String pathss = new String("");
		for (int i = 0; i < lists.length; i++) {

			if (lists[i].isFile()) {
				String fileName = lists[i].getName();
				String fileType = new String("");

				// 取得文件类型 2003
				fileType = fileName.substring((fileName.length() - 3), fileName
						.length());

				// 判断是否为doc文件
				if (fileType.equals("doc")) {
					System.out.println("当前正在转换......");

					// 打印当前目录路径
					System.out.println(paths);

					// 打印doc文件名
					System.out.println(fileName.substring(0,
							(fileName.length() - 4)));
					ActiveXComponent app = new ActiveXComponent(
							"Word.Application");// 启动word

					String docpath = paths + fileName;
					String htmlpath = savepaths
							+ fileName.substring(0, (fileName.length() - 4));

					String inFile = docpath;
					// 要转换的word文件
					String tpFile = htmlpath;
					// HTML文件

					boolean flag = false;

					try {
						app.setProperty("Visible", new Variant(false));

						// 设置word不可见
						Object docs = app.getProperty("Documents").toDispatch();
						Object doc = Dispatch.invoke(
								(Dispatch) docs,
								"Open",
								Dispatch.Method,
								new Object[] { inFile, new Variant(false),
										new Variant(true) }, new int[1])
								.toDispatch();

						//打开word文件
						Dispatch.invoke((Dispatch) doc, "SaveAs",
								Dispatch.Method, new Object[] { tpFile,
										new Variant(8) }, new int[1]);

						//作为html格式保存到临时文件
						Variant f = new Variant(false);
						Dispatch.call((Dispatch) doc, "Close", f);
						flag = true;
					} catch (Exception e) {
						e.printStackTrace();
					} finally {
						app.invoke("Quit", new Variant[] {});
					}
					System.out.println("转化完毕！");
				}

			} else {
				pathss = paths;
				//进入下一级目录
				pathss = pathss + lists[i].getName() + "";
				//递归遍历所有目录
				change(pathss, savepaths);
			}
		}
	}

	/**
	 * @Method: extractTextFromDOCX
	 * @Description: 从word 2007文档中提取纯文本
	 * 
	 * @param
	 * @return String
	 * @throws
	 */
	public static String extractTextFromDOC2007(String fileName)
			throws IOException, OpenXML4JException, XmlException {
		OPCPackage opcPackage = POIXMLDocument.openPackage(fileName);
		POIXMLTextExtractor ex = new XWPFWordExtractor(opcPackage);
		return ex.getText();
	}

	/**
	 * @Method: extractTextFromDOCX
	 * @Description: 从word 2003文档中提取纯文本
	 * 
	 * @param
	 * @return String
	 * @throws
	 */
	public static String extractTextFromDOC(InputStream is) throws IOException {
		WordExtractor ex = new WordExtractor(is); // is是WORD文件的InputStream
		return ex.getTextFromPieces();
		//		return ex.getHeaderText();

	}

	/**
	 * 用迭代法遍历指定目录下所有的文件
	 * @param strPath
	 */
	public static void refreshFileList(String strPath) {
		File dir = new File(strPath);
		File[] files = dir.listFiles();

		if (files == null)
			return;

		for (int i = 0; i < files.length; i++) {
			if (files[i].isDirectory()) {
				refreshFileList(files[i].getAbsolutePath());
			} else {
				String strFileName = files[i].getAbsolutePath().toLowerCase();
				//	                System.out.println("---"+strFileName);
				filelist.add(files[i].getAbsolutePath());
			}
		}
	}
}