JAVA读取PPT文件

import java.io.InputStream; import org.apache.lucene.document.Document; import org.apache.poi.hslf.HSLFSlideShow; import org.apache.poi.hslf.model.TextRun; import org.apache.poi.hslf.model.Slide; import org.apache.poi.hslf.usermodel.SlideShow; public Document getDocument(Index index, String url, String title, InputStream is) throws DocCenterException { StringBuffer content = new StringBuffer(""); try{ SlideShow ss = new SlideShow(new HSLFSlideShow(is));//is 为文件的InputStream，建立SlideShow Slide[] slides = ss.getSlides();//获得每一张幻灯片 for(int i=0;i<slides.length;i++){ TextRun[] t = slides[i].getTextRuns();//为了取得幻灯片的文字内容，建立TextRun for(int j=0;j<t.length;j++){ content.append(t[j].getText());//这里会将文字内容加到content中去 } content.append(slides[i].getTitle()); } index.AddIndex(url, title, content.toString()); }catch(Exception ex){ System.out.println(ex.toString()); } return null; }