diff options
Diffstat (limited to 'src/main/java/org/pdfbox/ExtractImages.java')
| -rw-r--r-- | src/main/java/org/pdfbox/ExtractImages.java | 210 |
1 files changed, 0 insertions, 210 deletions
diff --git a/src/main/java/org/pdfbox/ExtractImages.java b/src/main/java/org/pdfbox/ExtractImages.java deleted file mode 100644 index a8e46ee..0000000 --- a/src/main/java/org/pdfbox/ExtractImages.java +++ /dev/null @@ -1,210 +0,0 @@ -/**
- * Copyright (c) 2003-2004, www.pdfbox.org
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright notice,
- * this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright notice,
- * this list of conditions and the following disclaimer in the documentation
- * and/or other materials provided with the distribution.
- * 3. Neither the name of pdfbox; nor the names of its
- * contributors may be used to endorse or promote products derived from this
- * software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * http://www.pdfbox.org
- *
- */
-package org.pdfbox;
-
-import java.io.File;
-import java.io.IOException;
-
-import java.util.Iterator;
-import java.util.List;
-import java.util.Map;
-
-import org.pdfbox.pdmodel.PDDocument;
-import org.pdfbox.pdmodel.PDPage;
-import org.pdfbox.pdmodel.PDResources;
-
-import org.pdfbox.pdmodel.encryption.PDEncryptionDictionary;
-import org.pdfbox.pdmodel.encryption.PDStandardEncryption;
-import org.pdfbox.pdmodel.graphics.xobject.PDXObjectImage;
-
-/**
- * This will read a read pdf and extract images. <br/><br/>
- *
- * usage: java org.pdfbox.ExtractImages <pdffile> <password> [imageprefix]
- *
- * @author Ben Litchfield (ben@csh.rit.edu)
- * @version $Revision: 1.3 $
- */
-public class ExtractImages
-{
- private int imageCounter = 1;
-
- private static final String PASSWORD = "-password";
- private static final String PREFIX = "-prefix";
-
- /**
- * This is the entry point for the application.
- *
- * @param args The command-line arguments.
- *
- * @throws Exception If there is an error decrypting the document.
- */
- public static void main( String[] args ) throws Exception
- {
- ExtractImages extractor = new ExtractImages();
- extractor.extractImages( args );
- }
-
- private void extractImages( String[] args ) throws Exception
- {
- if( args.length < 1 || args.length > 3 )
- {
- usage();
- }
- else
- {
- String pdfFile = null;
- String password = "";
- String prefix = null;
- for( int i=0; i<args.length; i++ )
- {
- if( args[i].equals( PASSWORD ) )
- {
- i++;
- if( i >= args.length )
- {
- usage();
- }
- password = args[i];
- }
- else if( args[i].equals( PREFIX ) )
- {
- i++;
- if( i >= args.length )
- {
- usage();
- }
- prefix = args[i];
- }
- else
- {
- if( pdfFile == null )
- {
- pdfFile = args[i];
- }
- }
- }
- if( prefix == null && pdfFile.length() >4 )
- {
- prefix = pdfFile.substring( 0, pdfFile.length() -4 );
- }
-
- PDDocument document = null;
-
- try
- {
- document = PDDocument.load( pdfFile );
-
- if( document.isEncrypted() )
- {
- if( document.isOwnerPassword( password ) )
- {
- document.decrypt( password );
- }
- else
- {
- throw new IOException(
- "Error: You are only allowed to extract images with the owner password." );
- }
- }
-
- PDEncryptionDictionary encDictionary = document.getEncryptionDictionary();
-
- //only care about standard encryption and if it was decrypted with the
- //user password
- if( encDictionary instanceof PDStandardEncryption &&
- !document.wasDecryptedWithOwnerPassword() )
- {
- PDStandardEncryption stdEncryption = (PDStandardEncryption)encDictionary;
- if( !stdEncryption.canExtractContent() )
- {
- throw new IOException( "You do not have permission to extract images." );
- }
- }
-
- List pages = document.getDocumentCatalog().getAllPages();
- Iterator iter = pages.iterator();
- while( iter.hasNext() )
- {
- PDPage page = (PDPage)iter.next();
- PDResources resources = page.getResources();
- Map images = resources.getImages();
- if( images != null )
- {
- Iterator imageIter = images.keySet().iterator();
- while( imageIter.hasNext() )
- {
- String key = (String)imageIter.next();
- PDXObjectImage image = (PDXObjectImage)images.get( key );
- String name = getUniqueFileName( key, image.getSuffix() );
- System.out.println( "Writing image:" + name );
- image.write2file( name );
- }
- }
- }
- }
- finally
- {
- if( document != null )
- {
- document.close();
- }
- }
- }
- }
-
- private String getUniqueFileName( String prefix, String suffix )
- {
- String uniqueName = null;
- File f = null;
- while( f == null || f.exists() )
- {
- uniqueName = prefix + "-" + imageCounter;
- f = new File( uniqueName + "." + suffix );
- imageCounter++;
- }
- return uniqueName;
- }
-
- /**
- * This will print the usage requirements and exit.
- */
- private static void usage()
- {
- System.err.println( "Usage: java org.pdfbox.ExtractImages [OPTIONS] <PDF file>\n" +
- " -password <password> Password to decrypt document\n" +
- " -suffix <password> Image suffix(default to pdf name)\n" +
- " <PDF file> The PDF document to use\n"
- );
- System.exit( 1 );
- }
-
-}
\ No newline at end of file |