read every pagelink info from all annotations/actions, with apache pdfbox. (current page#, linkto page# and annotation coordinates.)

extract_pdf_links.java

	public static void main(String[] args) {
		try {
			File f = new File("../source.pdf");
			PDDocument pd = PDDocument.load(f);
			//PDFTextStripper textStripper = new PDFTextStripper();
			PDDocumentCatalog cat = pd.getDocumentCatalog();
			@SuppressWarnings("unchecked")
			List<PDPage> pages = cat.getAllPages();
			Iterator<PDPage> iter = pages.iterator();
			int pagenum = 1;
			while (iter.hasNext()) {
				PDPage page = (PDPage) iter.next();
				//PDResources resources = page.getResources();
				List<PDAnnotation> l = page.getAnnotations();
				Iterator<PDAnnotation> it = l.iterator();
				while (it.hasNext()) {
					PDAnnotation annotation = (PDAnnotation) it.next();
					if (annotation instanceof PDAnnotationLink) {
						// System.out.println(annotation);
						PDAnnotationLink link = (PDAnnotationLink) annotation;
						PDAction action = link.getAction();
						if(!(action instanceof PDActionGoTo)){
							continue;
						}
						PDActionGoTo go = (PDActionGoTo)action;
						PDPageDestination pdest = (PDPageDestination) go.getDestination();
						if(pdest.getPageNumber() > -1){
							continue;
						}
						int pdestnum = pages.indexOf(pdest.getPage()) + 1;
						PDRectangle rect = link.getRectangle();
						
						System.out.println("page: "+pagenum
							+" ,pgn: "+pdestnum
							+" ,base: "+rect.getLowerLeftX() + " " +rect.getLowerLeftY()
							+" ,size: "+rect.getWidth() +" "+rect.getHeight()
						);
					}
				}
				pagenum++;
			}
			pd.close();
		} catch (Exception ex) {
			ex.printStackTrace();
		}

	}