lucene-使用lius解析pdf、ppt、rtf、txt、xml

本文链接：https://blog.youkuaiyun.com/deepfuture/article/details/5063715

本文介绍了一个Java程序，用于从多种文件格式（包括PDF、PPT、RTF、TXT和XML）中提取文本内容的示例。该程序使用了不同的Indexer类来处理每种文件类型，并打印出了每种格式文件的前200个字符。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1、代码

package liusextract;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.UnsupportedEncodingException;

import lius.index.pdf.PdfIndexer;
import lius.index.powerpoint.PPTIndexer;
import lius.index.rtf.RTFIndexer;
import lius.index.txt.TXTIndexer;
import lius.index.xml.XmlFileIndexer;

public class pptandpdftest {

/**
* @param args
*/
public static void main(String[] args) {
  // TODO Auto-generated method stub
  //pdf
  PdfIndexer pi=new PdfIndexer();
  File f=new File("./htmls/readme.pdf");
  try {
   pi.setStreamToIndex(new FileInputStream(f));
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  String text1=pi.getContent().substring(0, 200);
  System.out.println("pdf:"+text1);
  //ppt
  PPTIndexer ppi=new PPTIndexer();
  f=new File("./htmls/123.ppt");
  try {
   ppi.setStreamToIndex(new FileInputStream(f));
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  String text2=ppi.getContent().substring(0, 200);
  System.out.println("ppt:"+text2);
  //rtf
  RTFIndexer rti=new RTFIndexer();
  f=new File("./htmls/111.rtf");
  try {
   rti.setStreamToIndex(new FileInputStream(f));
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  String text3=rti.getContent();
  try {
   text3=new String(text3.getBytes("ISO-8859-1"));
  } catch (UnsupportedEncodingException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  System.out.println("rtf:"+text3);
  //txt
  TXTIndexer ti=new TXTIndexer();
  f=new File("./htmls/readme.txt");
  try {
   ti.setStreamToIndex(new FileInputStream(f));
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  String text4=ti.getContent().substring(0, 200);
  System.out.println("txt:"+text4);
  //xml
  XmlFileIndexer xmli=new XmlFileIndexer();
  f=new File("./htmls/cd_catalog.xml");
  try {
   xmli.setStreamToIndex(new FileInputStream(f));
  } catch (FileNotFoundException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  String text5=xmli.getContent();
  try {
   text5=new String(text5.getBytes("ISO-8859-1"));
  } catch (UnsupportedEncodingException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  System.out.println("xml:"+text5);

}

}
2、效果