JAVA读取WORD,EXCEL,POWERPOINT,PDF文件的方法
来源:优易学  2011-11-29 16:15:45   【优易学:中国教育考试门户网】   资料下载   IT书店

 

  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;

  }

  PDF:

  import java.io.InputStream;

  import java.io.IOException;

  import org.apache.lucene.document.Document;

  import org.pdfbox.cos.COSDocument;

  import org.pdfbox.pdfparser.PDFParser;

  import org.pdfbox.pdmodel.PDDocument;

  import org.pdfbox.pdmodel.PDDocumentInformation;

  import org.pdfbox.util.PDFTextStripper;

  import com.search.code.Index;

  public Document getDocument(Index index, String url, String title, InputStream is)throws DocCenterException {

  COSDocument cosDoc = null;

  try {

  cosDoc = parseDocument(is);

  } catch (IOException e) {

  closeCOSDocument(cosDoc);

  throw new DocCenterException("无法处理该PDF文档", e);

  }

  if (cosDoc.isEncrypted()) {

  if (cosDoc != null)

  closeCOSDocument(cosDoc);

  throw new DocCenterException("该PDF文档是加密文档,无法处理");

  }

  String docText = null;

  try {

  PDFTextStripper stripper = new PDFTextStripper();

  docText = stripper.getText(new PDDocument(cosDoc));

  } catch (IOException e) {

  closeCOSDocument(cosDoc);

  throw new DocCenterException("无法处理该PDF文档", e);

  }

   PDDocument pdDoc = null;

  try {

  pdDoc = new PDDocument(cosDoc);

  PDDocumentInformation docInfo = pdDoc.getDocumentInformation();

  if(docInfo.getTitle()!=null && !docInfo.getTitle().equals("")){

  title = docInfo.getTitle();

  }

   } catch (Exception e) {

  closeCOSDocument(cosDoc);

  closePDDocument(pdDoc);

  System.err.println("无法取得该PDF文档的元数据" + e.getMessage());

  } finally {

  closeCOSDocument(cosDoc);

  closePDDocument(pdDoc);

  }

  return null;

  }

  private static COSDocument parseDocument(InputStream is) throws IOException {

  PDFParser parser = new PDFParser(is);

  parser.parse();

  return parser.getDocument();

  }

  private void closeCOSDocument(COSDocument cosDoc) {

  if (cosDoc != null) {

  try {

  cosDoc.close();

  } catch (IOException e) {

  }

  }

  }

  private void closePDDocument(PDDocument pdDoc) {

  if (pdDoc != null) {

  try {

  pdDoc.close();

  } catch (IOException e) {

  }

  }

  }

上一页  [1] [2] 

责任编辑:小草

文章搜索:
 相关文章
热点资讯
热门课程培训