Skip to content

Instantly share code, notes, and snippets.

@aisensiy
Created June 5, 2013 08:44
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save aisensiy/5712530 to your computer and use it in GitHub Desktop.
Save aisensiy/5712530 to your computer and use it in GitHub Desktop.
//package com.informit.poi;
// Import POI classes
import org.apache.poi.POIXMLDocument;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.extractor.ExtractorFactory;
import org.apache.poi.POITextExtractor;
// Import Java classes
import java.io.*;
import java.util.*;
public class WordSampleReader
{
public static void main( String[] args )
{
if( args.length == 0 )
{
System.out.println( "Usage: WordSampleReader " );
System.exit( 0 );
}
String filename = args[ 0 ];
System.out.println(filename);
try
{
POITextExtractor poitex = ExtractorFactory.createExtractor(new File(filename));
String text2007 = new String(poitex.getText().getBytes("GBK"));
System.out.println(text2007);
}
catch( Exception e )
{
e.printStackTrace();
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment