使用Java实现将ppt转换为文本

<!--PowerPoint 文档-->
<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-core</artifactId>
    <version>1.27</version> <!-- 使用最新版本 -->
</dependency>
<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-parsers</artifactId>
    <version>1.27</version> <!-- 使用最新版本 -->
</dependency>

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.sax.BodyContentHandler;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.web.multipart.MultipartFile;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
 
import java.io.IOException;
import java.io.InputStream;
 
public class PowerPointUtil {
 
    private static final Logger log = LoggerFactory.getLogger(PowerPointUtil.class);
 
    /**
     * 将 PowerPoint 文档转换为文本
     *
     * @param file PowerPoint 文件
     * @return 提取的文本
     */
    public static String pptToTextConverter(MultipartFile file) {
        try (InputStream is = file.getInputStream()) {
            return extractTextUsingTika(is);
        } catch (IOException e) {
            throw new RuntimeException("无法读取PowerPoint文档", e);
        }
    }
 
    private static String extractTextUsingTika(InputStream is) {
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();
 
        try {
            new OOXMLParser().parse(is, handler, metadata, context);
            String text = handler.toString();
            log.info("PowerPoint文档内容: {}", text);
            return text;
        } catch (IOException | TikaException | SAXException e) {
            throw new RuntimeException("提取PowerPoint文档内容时发生错误", e);
        }
    }
}