How to extract hyperlink information PDFBox

Question

I am trying to extract the hyperlink information from a PDF using PDFBox but I am unsure how to get

for( Object p : pages ) {
    PDPage page = (PDPage)p;

    List<?> annotations = page.getAnnotations();
    for( Object a : annotations ) {
        PDAnnotation annotation = (PDAnnotation)a;

        if( annotation instanceof PDAnnotationLink ) {
            PDAnnotationLink link = (PDAnnotationLink)annotation;
            System.out.println(link.toString());
            System.out.println(link.getDestination());

        }
    }

}

I want to extract the url of the hyperlink destination and the text of the hyperlink. How can one do this?

Thanks

Answer 1

If you need a simple links extractor, follow snippet

public List<String> extractLinks(String url) {
    try{
        InputStream pdfStream = new URL(url).openStream();
        List<String> links = new ArrayList<>();
        try (PDDocument document = PDDocument.load(pdfStream)) {
            document.getPages().forEach(page -> {
                try {
                    List<PDAnnotation> annotations = page.getAnnotations();
                    for (PDAnnotation annotation : annotations) {
                        if (annotation instanceof PDAnnotationLink) {
                            PDAnnotationLink link = (PDAnnotationLink) annotation;
                            if (link.getAction() instanceof PDActionURI) {
                                PDActionURI uri = (PDActionURI) link.getAction();
                                links.add(uri.getURI());
                            }
                        }
                    }
                } catch (IOException e) {
                    e.printStackTrace();
                }
            });
        } catch (IOException e) {
            e.printStackTrace();
        }
        return links;
    }catch (Exception e){
        LOGGER.error("Error to extract links");
        return new ArrayList<>();
    }
}

Answer 2

03/21/2023
I have Just tested today and it work. but there are couple of set up need to do. this is how i did it.
[dependency]
    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.27</version>
    </dependency>

Imports:-
import java.awt.geom.Rectangle2D;
import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
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;

public class Test_newSome {

    public static void main(String[] args) throws IOException {
// File path = open pdf file on MSEdge and copy url 
        URL url = new URL("file:///C:/Users/PcuserName/Downloads/Credentials%20Email%20-%20Mar21FN%20Mar21094806LN.pdf");
        InputStream is = url.openStream();
        BufferedInputStream filePase = new BufferedInputStream(is);
        PDDocument doc = null;

        doc = PDDocument.load(filePase);

        for (PDPage page : doc.getPages()) {
            int pageNum = 0;
            pageNum++;
            PDFTextStripperByArea stripper = new PDFTextStripperByArea();
            List<PDAnnotation> annotations = page.getAnnotations();
            // first setup text extraction regions
            for (int j = 0; j < annotations.size(); j++) {
                PDAnnotation annot = annotations.get(j);
                if (annot instanceof PDAnnotationLink) {
                    PDAnnotationLink link = (PDAnnotationLink) annot;
                    PDRectangle rect = link.getRectangle();
                    // need to reposition link rectangle to match text space
                    float x = rect.getLowerLeftX();
                    float y = rect.getUpperRightY();
                    float width = rect.getWidth();
                    float height = rect.getHeight();
                    int rotation = page.getRotation();
                    if (rotation == 0) {
                        PDRectangle pageSize = page.getMediaBox();
                        y = pageSize.getHeight() - y;
                    } else if (rotation == 90) {
                        // do nothing
                    }

                    Rectangle2D.Float awtRect = new Rectangle2D.Float(x, y, width, height);
                    stripper.addRegion("" + j, awtRect);
                }
            }

            stripper.extractRegions(page);

            for (int j = 0; j < annotations.size(); j++) {
                PDAnnotation annot = annotations.get(j);
                if (annot instanceof PDAnnotationLink) {
                    PDAnnotationLink link = (PDAnnotationLink) annot;
                    PDAction action = link.getAction();
                    String urlText = stripper.getTextForRegion("" + j);
                    if (action instanceof PDActionURI) {
                        PDActionURI uri = (PDActionURI) action;
                        System.out.println("Page " + pageNum + ":'" + urlText.trim() + "'=" + uri.getURI());

                    }
                }
            }
        }
    }
}

Answer 3

Use this code from the PrintURLs sample code from the source code download:

for( PDPage page : doc.getPages() )
{
    pageNum++;
    PDFTextStripperByArea stripper = new PDFTextStripperByArea();
    List<PDAnnotation> annotations = page.getAnnotations();
    //first setup text extraction regions
    for( int j=0; j<annotations.size(); j++ )
    {
        PDAnnotation annot = annotations.get(j);
        if( annot instanceof PDAnnotationLink )
        {
            PDAnnotationLink link = (PDAnnotationLink)annot;
            PDRectangle rect = link.getRectangle();
            //need to reposition link rectangle to match text space
            float x = rect.getLowerLeftX();
            float y = rect.getUpperRightY();
            float width = rect.getWidth();
            float height = rect.getHeight();
            int rotation = page.getRotation();
            if( rotation == 0 )
            {
                PDRectangle pageSize = page.getMediaBox();
                y = pageSize.getHeight() - y;
            }
            else if( rotation == 90 )
            {
                //do nothing
            }

            Rectangle2D.Float awtRect = new Rectangle2D.Float( x,y,width,height );
            stripper.addRegion( "" + j, awtRect );
        }
    }

    stripper.extractRegions( page );

    for( int j=0; j<annotations.size(); j++ )
    {
        PDAnnotation annot = annotations.get(j);
        if( annot instanceof PDAnnotationLink )
        {
            PDAnnotationLink link = (PDAnnotationLink)annot;
            PDAction action = link.getAction();
            String urlText = stripper.getTextForRegion( "" + j );
            if( action instanceof PDActionURI )
            {
                PDActionURI uri = (PDActionURI)action;
                System.out.println( "Page " + pageNum +":'" + urlText.trim() + "'=" + uri.getURI() );
            }
        }
    }
}

It works in two parts, one is getting the URL which is easy, the other is getting the URL text, which is done with a text extraction at the rectangle of the annotation.

Answer 4

We must get hyperlink information and internal link(ex. move page....). I using code below:

int pageNum = 0;
            for (PDPage page : originalPDF.getPages()) {
                pageNum++;
                List<PDAnnotation> annotations = page.getAnnotations();
                for (PDAnnotation annot : annotations) {
                    if (annot instanceof PDAnnotationLink) {
                        // get dimension of annottations
                        PDAnnotationLink link = (PDAnnotationLink) annot;
                        // get link action include link url and internal link
                        PDAction action = link.getAction();
                        // get link internal some case specal
                        PDDestination pDestination = link.getDestination();

                        if (action != null) {
                            if (action instanceof PDActionURI || action instanceof PDActionGoTo) {
                                if (action instanceof PDActionURI) {
                                    // get uri link
                                    PDActionURI uri = (PDActionURI) action;
                                    System.out.println("uri link:" + uri.getURI());
                                } else {
                                    if (action instanceof PDActionGoTo) {
                                        // get internal link
                                        PDDestination destination = ((PDActionGoTo) action).getDestination();
                                        PDPageDestination pageDestination;
                                        if (destination instanceof PDPageDestination) {
                                            pageDestination = (PDPageDestination) destination;
                                        } else {
                                            if (destination instanceof PDNamedDestination) {
                                                pageDestination = originalPDF.getDocumentCatalog().findNamedDestinationPage((PDNamedDestination) destination);
                                            } else {
                                                // error handling
                                                break;
                                            }
                                        }

                                        if (pageDestination != null) {
                                            System.out.println("page move: " + (pageDestination.retrievePageNumber() + 1));
                                        }
                                    }
                                }
                            }
                        } else {
                            if (pDestination != null) {
                                PDPageDestination pageDestination;
                                if (pDestination instanceof PDPageDestination) {
                                    pageDestination = (PDPageDestination) pDestination;
                                } else {
                                    if (pDestination instanceof PDNamedDestination) {
                                        pageDestination = originalPDF.getDocumentCatalog().findNamedDestinationPage((PDNamedDestination) pDestination);
                                    } else {
                                        // error handling
                                        break;
                                    }
                                }

                                if (pageDestination != null) {
                                    System.out.println("page move: " + (pageDestination.retrievePageNumber() + 1));
                                }
                            } else {
                                //    
                            }
                        }
                    }
                }

            }