cloudfile/doc-common/src/main/java/com/doc/common/utils/PPT.java

package com.doc.common.utils;

import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hslf.usermodel.HSLFSlide;
import org.apache.poi.sl.usermodel.Slide;
import org.apache.poi.sl.usermodel.SlideShow;
import org.apache.poi.sl.usermodel.TextRun;
import org.apache.poi.xslf.usermodel.XMLSlideShow;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

public class PPT {
    //直接抽取幻灯片的全部内容
    public static String readDoc1(InputStream is) throws IOException {
        PowerPointExtractor extractor = new PowerPointExtractor(is);
        return extractor.getText();
    }

    //一张幻灯片一张幻灯片地读取
    public static void readDoc2(InputStream is) throws IOException {
        SlideShow ss = new XMLSlideShow(is);
        List<Slide> slides = ss.getSlides();
        for (Slide slide : slides) {
            //读取一张幻灯片的标题
            String title = slide.getTitle();
            System.out.println("标题:" + title);
//            //读取一张幻灯片的内容(包括标题)

            List<TextRun> runs = slide.getComments();
            for (TextRun run:runs) {
                System.out.println(run.getRawText());
            }
        }
    }

    public static void main(String[] args) {
        File file = new File("D:\\SYSTEM\\Desktop\\temp\\测试ppt.pptx");
        try (FileInputStream is = new FileInputStream(file)){
            SlideShow ppt=new XMLSlideShow(is);

            List<HSLFSlide> slides = ppt.getSlides();
            for (HSLFSlide slide : slides) {
                System.err.println(slide.getTitle());
                System.err.println(slide.getComments());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}