用Java从DOC文件中提取嵌入式ZIP

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.poifs.filesystem.DirectoryEntry;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;

public class ExtractEmbeddedZipFromDoc {
    public static void main(String[] args) {
        try {
            // 加载DOC文件
            POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream("example.doc"));

            // 创建WordExtractor对象，用于提取DOC文件中的文本内容
            HWPFDocument doc = new HWPFDocument(fs);
            WordExtractor extractor = new WordExtractor(doc);

            // 获取嵌入式对象的数量
            int numEmbeddedObjects = doc.getEmbeddedObjects().getCount();

            // 遍历嵌入式对象
            for (int i = 0; i < numEmbeddedObjects; i++) {
                // 获取嵌入式对象的输入流
                InputStream embeddedObjectStream = doc.getEmbeddedObjects().getObject(i).getInputStream();

                // 创建目标文件
                FileOutputStream outputStream = new FileOutputStream("extracted" + i + ".zip");

                // 将嵌入式ZIP文件写入目标文件
                byte[] buffer = new byte[1024];
                int length;
                while ((length = embeddedObjectStream.read(buffer)) > 0) {
                    outputStream.write(buffer, 0, length);
                }

                // 关闭流
                embeddedObjectStream.close();
                outputStream.close();
            }

            // 提取DOC文件中的文本内容
            String text = extractor.getText();
            System.out.println(text);

            // 关闭WordExtractor和POIFSFileSystem
            extractor.close();
            fs.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}