[PDFBOX-1240] Extract Images from PDF file using PDFBox in C#

• Type: New Feature
• Status: Closed
• Priority: Minor
• Resolution: Not A Problem
• Affects Version/s: 0.7.3
• Component/s: Utilities
• Assignee: Andreas Lehmkühler
• Reporter: Pham Minh Cuong
• Created: 29/Feb/12 03:41
• Updated: 21/May/12 04:58
• Resolved: 21/May/12 04:58

Description

public class ExtractImage
{
private int imageCounter = 1;
private static string PASSWORD = "-password";
private static string PREFIX = "-prefix";

public ExtractImage()
{

}

public void extractImage(string []args)
{
if(args.Length<1||args.Length>4)

{ usage(); }

else
{
string pdfFile = "";
string password = "";
string prefix = null;
for (int i = 0; i < args.Length; i++)
{
if(args[i]==PASSWORD)
{
i++;
if (i >= args.Length)

{ usage(); }
password = args[i];
}
else if (args[i]==PREFIX)
{
i++;
if(i>=args.Length)
{ usage(); }

prefix = args[i];
}
else
{
if(pdfFile==null)

{ pdfFile = args[i]; }

}
}
if(pdfFile==null)

{ usage(); }

else
{
if(prefix==null && pdfFile.Length>4)

{ prefix = pdfFile.Substring(0, pdfFile.Length - 4); }

PDDocument document=null;
try
{
document = PDDocument.load(pdfFile);
if( document.isEncrypted() )
{

StandardDecryptionMaterial spm = new StandardDecryptionMaterial(password);
document.openProtection(spm);
AccessPermission ap = document.getCurrentAccessPermission();

if( ! ap.canExtractContent() )

{ Console.WriteLine("Error: You do not have permission to extract images." ); }

}

List pages = document.getDocumentCatalog().getAllPages();
java.util.Iterator iter = pages.iterator();
while( iter.hasNext() )
{
PDPage page = (PDPage)iter.next();
PDResources resources = page.getResources();
java.util.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() ); Console.WriteLine( "Writing image:" + name ); image.write2file( name ); }

}
}
}
catch (Exception)

{ throw; }

}
}
}

private string getUniqueFileName(string prefix, string suffix)
{
string uniqueName = null;
java.io.File f = null;
f = null;
while (f == null || f.exists())

{ uniqueName = prefix + "-" + imageCounter; f =new File(uniqueName + "." + suffix); imageCounter++; }

return uniqueName;
}

private void usage()

{ Console.Error.WriteLine("Usage: java org.pdfbox.ExtractImages [OPTIONS] <PDF file>\n" + " -password <password> Password to decrypt document\n" + " -prefix <image-prefix> Image prefix(default to pdf name)\n" + " <PDF file> The PDF document to use\n"); Environment.Exit(1); }

}

Reference: http://svn.apache.org/repos/asf/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/ExtractImages.java
I tested but i have a problem.It ran if(args.Length<1||args.Length>4) and stopped in usage().It loop.Please help me.Many thanks.

{ usage(); }