下载lius

http://sourceforge.net/projects/lius/

1、解析word

package liusextract;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;

import lius.index.msword.WordIndexer;

public class wordtest {

/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
WordIndexer wi=new WordIndexer();
File f=new File("./htmls/ddd.doc");
try {
wi.setStreamToIndex(new FileInputStream(f));
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
String text=wi.getContent();
System.out.print(text);

}

}

效果

2、excel

package liusextract;
import lius.index.excel.ExcelIndexer;
import java.io.*;

public class exceltest {

/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
ExcelIndexer ei=new ExcelIndexer();
File f=new File("./htmls/book1.xls");
try {
ei.setStreamToIndex(new FileInputStream(f));
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
String text=ei.getContent();
System.out.print(text);

}

}