Java 实战：基于 Spire.Doc 高效提取 Word 文档文本与图片

<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>14.7.4</version>
    </dependency>
</dependencies>

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

public class ExtractText {
    public static void main(String[] args) throws IOException {
        // 1. 创建文档对象并加载本地Word文档
        Document document = new Document();
        document.loadFromFile("sample1.docx");

        // 2. 提取文档全部文本内容
        String text=document.getText();

        // 3. 将文本写入本地TXT文件
        writeStringToTxt(text,"ExtractedText.txt");
        System.out.println("Word文本提取完成，已保存至ExtractedText.txt");
    }

    /**
     * 文本内容写入TXT文件工具方法
     * @param content 提取的文本内容
     * @param txtFileName 输出文件名
     * @throws IOException IO异常
     */
    public static void writeStringToTxt(String content, String txtFileName) throws IOException{
        // 追加模式写入文件
        FileWriter fWriter= new FileWriter(txtFileName,true);
        try {
            fWriter.write(content);
        }catch(IOException ex){
            ex.printStackTrace();
        }finally{
            // 强制刷新流并关闭资源，避免内存泄漏
            try{
                fWriter.flush();
                fWriter.close();
            } catch (IOException ex) {
                ex.printStackTrace();
            }
        }
    }
}

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.*;
import java.util.*;

public class ExtractImage {
    public static void main(String[] args) throws IOException {
        // 1. 加载Word文档
        Document document = new Document();
        document.loadFromFile("sample2.docx");

        // 2. 初始化队列，遍历文档树形节点
        Queue<ICompositeObject> nodes = new LinkedList<>();
        nodes.add(document);
        List<BufferedImage> images = new ArrayList<>();

        // 3. 深度遍历文档，筛选图片节点
        while (nodes.size() > 0) {
            ICompositeObject node = nodes.poll();
            for (int i = 0; i < node.getChildObjects().getCount(); i++)
            {
                IDocumentObject child = node.getChildObjects().get(i);
                // 递归添加复合节点，继续深度遍历
                if (child instanceof ICompositeObject)
                {
                    nodes.add((ICompositeObject) child);
                }
                // 识别图片节点并收集图片
                else if (child.getDocumentObjectType() == DocumentObjectType.Picture)
                {
                    DocPicture picture = (DocPicture) child;
                    images.add(picture.getImage());
                }
            }
        }

        // 4. 创建输出目录，批量保存图片
        File outputDir = new File("output");
        if (!outputDir.exists()){
            outputDir.mkdirs();
        }
        for (int i = 0; i < images.size(); i++) {
            File file = new File(String.format("output/extractImage-%d.png", i));
            ImageIO.write(images.get(i), "PNG", file);
        }
        System.out.println("图片提取完成，共提取"+images.size()+"张图片");
    }
}