使用WordExtractor读取Word文档,请先下载 tm-extractors-0.4.jar
- import java.io.FileInputStream;
- import org.textmining.text.extraction.WordExtractor;
- public class WordTest {
- public static void main(String args[]) throws Exception {
- new WordTest().readByOther();
- }
- public void readByText() throws Exception {
- FileInputStream in = new FileInputStream("C://test.doc ");
- WordExtractor extractor = new WordExtractor();
- String str = extractor.extractText(in);
- System.out.println(str);
- }
- }