下面用到一个插件 插件可以下载在下面:实例代码如下
import java.io.File;
import java.io.FileInputStream;
import java.util.Date;
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 text;
}
public static void main(String[] args) {
Date startDate = new Date();
try {
String text = WordReader.readDoc("F:/aa.doc");
System.out.println(text);
} catch (Exception e) {
e.printStackTrace();
}
Date endDate = new Date();
System.out.println(endDate.getTime()-startDate.getTime()+"ms");
}
}