wordreader.java

利用 JAVA 抽取 word 文本内容

import java.io.*; 
import org.textmining.text.extraction.WordExtractor; 


public class WordReader
{ 
	public static String readDoc(String doc) throws Exception 
	{
		try{
			// 创建输入流读取DOC文件
			FileInputStream in = new FileInputStream(new File(doc));
			WordExtractor extractor = null;
			String text = null;
			extractor = new WordExtractor();
			try{
				text = extractor.extractText(in);
			}catch(Exception e){
				text = null;
			}
			in.close();
			return text;
		}catch(Exception e){
			e.printStackTrace();
			return null;
		}
	}
	
	public static void main(String args[]) throws Exception 
	{ 
		if(args.length>0)
		{
			try{
			   String text = WordReader.readDoc(args[0]);
			   System.out.println(text);
			}catch(Exception e){
				e.printStackTrace();
			}			
		}
	} 
}