Как вытащить текст из .doc или .docx на java?

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21

import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import java.io.FileInputStream;
import java.io.IOException;

public class DocxTextExtractor {
    public static void main(String[] args) {
        try {
            FileInputStream fis = new FileInputStream("example.docx");
            XWPFDocument document = new XWPFDocument(fis);
            XWPFWordExtractor extractor = new XWPFWordExtractor(document);
            String text = extractor.getText();
            System.out.println(text);
            extractor.close();
            document.close();
            fis.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

1
2
3
4
5

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>4.1.2</version>
</dependency>

1

compile group: 'org.apache.poi', name: 'poi', version: '4.1.2'

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

import org.apache.tika.Tika;

import java.io.FileInputStream;
import java.io.IOException;

public class DocxTextExtractor {
    public static void main(String[] args) {
        try {
            Tika tika = new Tika();
            String text = tika.parseToString(new FileInputStream("example.docx"));
            System.out.println(text);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}