Java提取Word文档文本与图片的完整方法

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.doc</artifactId>
        <version>14.6.0</version>
    </dependency>
</dependencies>

import com.spire.doc.Document;
import java.io.FileWriter;
import java.io.IOException;

public class ExtractTextDemo {
    public static void main(String[] args) throws IOException {
        Document document = new Document();
        document.loadFromFile("示例文档.docx");

        // 获取文档中的全部文本
        String text = document.getText();

        // 写入文本文件
        try (FileWriter writer = new FileWriter("文档文本内容.txt")) {
            writer.write(text);
        }

        document.dispose();
    }
}

import com.spire.doc.Document;
import com.spire.doc.DocumentObjectType;
import com.spire.doc.fields.DocPicture;
import com.spire.doc.interfaces.IDocumentObject;
import com.spire.doc.interfaces.ICompositeObject;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.util.LinkedList;
import java.util.Queue;

public class ExtractImagesDemo {
    public static void main(String[] args) throws IOException {
        Document document = new Document();
        document.loadFromFile("示例文档.docx");

        Queue<ICompositeObject> nodes = new LinkedList<>();
        nodes.add(document);

        int imageIndex = 0;

        while (!nodes.isEmpty()) {
            ICompositeObject node = nodes.poll();
            for (int i = 0; i < node.getChildObjects().getCount(); i++) {
                IDocumentObject child = node.getChildObjects().get(i);

                if (child instanceof ICompositeObject) {
                    nodes.add((ICompositeObject) child);
                } else if (child.getDocumentObjectType() == DocumentObjectType.Picture) {
                    DocPicture picture = (DocPicture) child;
                    BufferedImage image = picture.getImage();
                    File outputFile = new File(String.format("图片_%d.png", imageIndex++));
                    ImageIO.write(image, "PNG", outputFile);
                }
            }
        }

        document.dispose();
        System.out.println("共提取图片：" + imageIndex + " 张");
    }
}

import com.spire.doc.Document;
import com.spire.doc.Comment;
import com.spire.doc.documents.Paragraph;

public class ExtractCommentsDemo {
    public static void main(String[] args) {
        Document doc = new Document();
        doc.loadFromFile("含批注的文档.docx");

        for (int i = 0; i < doc.getComments().getCount(); i++) {
            Comment comment = doc.getComments().get(i);
            System.out.println("批注 #" + (i + 1) + ":");
            for (int j = 0; j < comment.getBody().getParagraphs().getCount(); j++) {
                Paragraph para = comment.getBody().getParagraphs().get(j);
                System.out.println(para.getText());
            }
        }

        doc.dispose();
    }
}