org.apache.pdfbox.examples.pdmodel.PrintURLs Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of pdfbox-examples Show documentation

The Apache PDFBox library is an open source Java tool for working with PDF documents. This artefact contains examples on how the library can be used.

There is a newer version: 3.0.3

Show newest version

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.pdfbox.examples.pdmodel;

import java.awt.geom.Rectangle2D;
import java.io.File;
import java.io.IOException;
import java.util.List;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.interactive.action.PDAction;
import org.apache.pdfbox.pdmodel.interactive.action.PDActionURI;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationLink;
import org.apache.pdfbox.text.PDFTextStripperByArea;


/**
 * This is an example of how to access a URL in a PDF document.
 *
 * @author Ben Litchfield
 */
public final class PrintURLs
{
    /**
     * Constructor.
     */
    private PrintURLs()
    {
        //utility class
    }

    /**
     * This will create a hello world PDF document.
     * 

     * see usage() for commandline
     *
     * @param args Command line arguments.
     *
     * @throws IOException If there is an error extracting the URLs.
     */
    public static void main(String[] args) throws IOException
    {
        PDDocument doc = null;
        try
        {
            if( args.length != 1 )
            {
                usage();
            }
            else
            {
                doc = PDDocument.load( new File(args[0]) );
                int pageNum = 0;
                for( PDPage page : doc.getPages() )
                {
                    pageNum++;
                    PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                    List annotations = page.getAnnotations();
                    //first setup text extraction regions
                    for( int j=0; j" );
    }
}