Hi
I am working with the PDFBox where i want to convert pdf2txt ,encrypt and decrypt pdfs.
i have downloaded the software from
here is the link:
SourceForge.net: PDFBox
i want this:
PDF Box:
http://incubator.apache.o...ineutilities/Encrypt.html
Here is my code snippet for TextExtraction from a PDF:
|
Code:
|
package com.pdfBox;
import java.io.File;
import java.io.FileOutputStream ;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer ;
import java.net.MalformedURLException ;
import java.net.URL ;
import org.pdfbox.util.operator.OperatorProcessor;
import org.pdfbox.util.PDFStreamEngine;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.encryption.AccessPermission;
import org.pdfbox.pdmodel.encryption.StandardDecryptionMaterial;
import org.pdfbox.util.PDFText2HTML;
import org.pdfbox.util.PDFTextStripper;
public class ExtractText
{
/**
* This is the default encoding of the text to be output.
*/
public static final String DEFAULT_ENCODING =
null;
//"ISO-8859-1";
//"ISO-8859-6"; //arabic
//"US-ASCII";
//"UTF-8";
//"UTF-16";
//"UTF-16BE";
//"UTF-16LE";
private static final String PASSWORD = "-password";
private static final String ENCODING = "-encoding";
private static final String CONSOLE = "-console";
private static final String START_PAGE = "-startPage";
private static final String END_PAGE = "-endPage";
private static final String SORT = "-sort";
private static final String HTML = "-html"; // jjb - added simple HTML output
/**
* private constructor.
*/
private ExtractText()
{
//static class
}
/**
* Infamous main method.
*
* @param args Command line arguments, should be one and a reference to a file.
*
* @throws Exception If there is an error parsing the document.
*/
public static void main( String [] arg ) throws Exception
{
boolean toConsole = false;
OperatorProcessor pr=null;
boolean toHTML = false;
boolean sort = false;
String password = "";
String encoding = DEFAULT_ENCODING;
String pdfFile = null;
String textFile = null;
int startPage = 1;
int endPage = Integer.MAX_VALUE;
String args[]={"C:\\101_NY.pdf","C:\\101_NY.txt"};
for( int i=0; i<args.length; i++ )
{
if( args.equals( PASSWORD ) )
{
i++;
if( i >= args.length )
{
usage();
}
password = args;
}
else if( args.equals( ENCODING ) )
{
i++;
if( i >= args.length )
{
usage();
}
encoding = args;
}
else if( args.equals( START_PAGE ) )
{
i++;
if( i >= args.length )
{
usage();
}
startPage = Integer.parseInt( args );
}
else if( args.equals( HTML ) )
{
toHTML = true;
}
else if( args.equals( SORT ) )
{
sort = true;
}
else if( args.equals( END_PAGE ) )
{
i++;
if( i >= args.length )
{
usage();
}
endPage = Integer.parseInt( args );
}
else if( args.equals( CONSOLE ) )
{
toConsole = true;
}
else
{
if( pdfFile == null )
{
pdfFile = args;
}
else
{
textFile = args;
}
}
}
if( pdfFile == null )
{
usage();
}
else
{
Writer output = null;
PDDocument document = null;
try
{
try
{
//basically try to load it from a url first and if the URL
//is not recognized then try to load it from the file system.
URL url = new URL ( pdfFile );
document = PDDocument.load( url );
String fileName = url.getFile();
if( textFile == null && fileName.length() >4 )
{
File outputFile =
new File ( fileName.substring( 0, fileName.length() -4 ) + ".txt" );
textFile = outputFile.getName();
}
}
catch( MalformedURLException e )
{
document = PDDocument.load( pdfFile );
if( textFile == null && pdfFile.length() >4 )
{
textFile = pdfFile.substring( 0, pdfFile.length() -4 ) + ".txt";
}
}
//document.print();
if( document.isEncrypted() )
{
StandardDecryptionMaterial sdm = new StandardDecryptionMaterial( password );
document.openProtection( sdm );
AccessPermission ap = document.getCurrentAccessPermission();
if( ! ap.canExtractContent() )
{
throw new IOException ( "You do not have permission to extract text" );
}
}
if( toConsole )
{
output = new OutputStreamWriter ( System.out );
}
else
{
if( encoding != null )
{
output = new OutputStreamWriter (
new FileOutputStream ( textFile ), encoding );
}
else
{
//use default encoding
output = new OutputStreamWriter (
new FileOutputStream ( textFile ) );
}
}
PDFTextStripper stripper = null;
if(toHTML)
{
stripper = new PDFText2HTML();
}
else
{
stripper = new PDFTextStripper();
}
stripper.setSortByPosition( sort );
stripper.setStartPage( startPage );
stripper.setEndPage( endPage );
stripper.writeText( document, output );
}
finally
{
if( output != null )
{
output.close();
}
if( document != null )
{
document.close();
}
}
}//test
}
/**
* This will print the usage requirements and exit.
*/
private static void usage()
{
System.err.println( "Usage: java org.pdfbox.ExtractText [OPTIONS] <PDF file> [Text File]\n" +
" -password <password> Password to decrypt document\n" +
" -encoding <output encoding> (ISO-8859-1,UTF-16BE,UTF-16LE,...)\n" +
" -console Send text to console instead of file\n" +
" -html Output in HTML format instead of raw text\n" +
" -sort Sort the text before writing\n" +
" -startPage <number> The first page to start extraction(1 based)\n" +
" -endPage <number> The last page to extract(inclusive)\n" +
" <PDF file> The PDF document to use\n" +
" [Text File] The file to write the text to\n"
);
System.exit( 1 );
}
} |
i got this error:
Exception in thread "main" java.lang.NoSuchMethodError: org.pdfbox.util.operator.OperatorProcessor.setCont ext(Lorg/pdfbox/util/PDFStreamEngine
V
at org.pdfbox.util.PDFStreamEngine.registerOperatorPr ocessor(PDFStreamEngine.java:140)
at org.pdfbox.util.PDFStreamEngine.<init>(PDFStreamEn gine.java:123)
at org.pdfbox.util.PDFTextStripper.<init>(PDFTextStri pper.java:119)
at com.pdfBox.ExtractText.main(ExtractText.java:204)
----------------------------------------------------------------------------------------
Even i tried with the exe's which are given with the softwares..
i can nt run those....
can u help me please..
PDF Box issue
Linear Mode
