62,614
社区成员
发帖
与我相关
我的任务
分享
import java.io.File;
import java.io.FileInputStream;
import org.textmining.text.extraction.WordExtractor;
public class WordReader {
public static String readDoc(String doc) throws Exception {
// 创建输入流读取doc文件
FileInputStream in = new FileInputStream(new File(doc));
WordExtractor extractor = null;
String text = null;
// 创建WordExtractor
extractor = new WordExtractor();
// 对doc文件进行提取
text = extractor.extractText(in);
return new String(text.getBytes(), "Ksphonet.ttf");
}
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
try{
String text = WordReader.readDoc("docfile//word1.doc");
System.out.println(text);
}catch(Exception ex){
ex.printStackTrace();
}
}
}