Java实现从Word文档中提取文本和图像

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.com/nexus/content/groups/public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.doc</artifactId>
        <version>14.3.1</version>
    </dependency>
</dependencies>

import com.spire.doc.Document;
import java.io.FileWriter;
import java.io.IOException;
public class ExtractTextFromWord {
    public static void main(String[] args) throws IOException {
        // 创建 Document 对象并加载 Word 文档
        Document document = new Document();
        document.loadFromFile("sample.docx");
        // 获取文档全部文本
        String text = document.getText();
        // 保存为 TXT 文件
        writeStringToTxt(text, "extracted_text.txt");
        System.out.println("文本提取完成，已保存至 extracted_text.txt");
    }
    private static void writeStringToTxt(String content, String txtFileName) throws IOException {
        try (FileWriter writer = new FileWriter(txtFileName)) {
            writer.write(content);
        }
    }
}

import com.spire.doc.*;
import com.spire.doc.documents.*;
import com.spire.doc.fields.*;
import com.spire.doc.interfaces.*;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.util.*;

public class ExtractImagesFromWord {
    public static void main(String[] args) throws IOException {
        // 加载文档
        Document document = new Document();
        document.loadFromFile("sample.docx");

        // BFS 遍历队列
        Queue<ICompositeObject> nodes = new LinkedList<>();
        nodes.add(document);

        // 存储提取的图像
        List<BufferedImage> images = new ArrayList<>();

        // 遍历文档树
        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) {
                    // 复合对象继续入队
                    nodes.add((ICompositeObject) child);
                } else if (child.getDocumentObjectType() == DocumentObjectType.Picture) {
                    // 提取图像
                    DocPicture picture = (DocPicture) child;
                    images.add(picture.getImage());
                }
            }
        }

        // 保存所有图像（确保 output 目录存在）
        File outputDir = new File("output");
        if (!outputDir.exists()) {
            outputDir.mkdirs();
        }
        for (int i = 0; i < images.size(); i++) {
            File file = new File(outputDir, String.format("image_%d.png", i));
            ImageIO.write(images.get(i), "PNG", file);
            System.out.println("已保存图像: " + file.getName());
        }

        System.out.println("共提取 " + images.size() + " 张图像");
    }
}