Some test text!

menu

Read elements across all PDF pages in Java

More languages

chevron_right
More languages
JavaScript
Java (Android)
C++
C#
C# (.NET Core)
Java
Kotlin
Obj-C
JS (Node.js)
PHP
Python
Ruby
Swift
C# (UWP)
VB
C# (Xamarin)

Sample Java code for using PDFTron SDK to traverse the page display list using ElementReader. Learn more about our Java PDF Library and PDF Parsing & Content Extraction Library.

Get StartedSamplesDownload

To run this sample, get started with a free trial of PDFTron SDK.

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

package com.pdftron.android.pdfnetsdksamples.samples;

import com.pdftron.android.pdfnetsdksamples.OutputListener;
import com.pdftron.android.pdfnetsdksamples.PDFNetSample;
import com.pdftron.android.pdfnetsdksamples.R;
import com.pdftron.android.pdfnetsdksamples.util.Utils;
import com.pdftron.common.PDFNetException;
import com.pdftron.pdf.Element;
import com.pdftron.pdf.ElementReader;
import com.pdftron.pdf.PDFDoc;
import com.pdftron.pdf.PageIterator;
import com.pdftron.pdf.PathData;

import java.util.ArrayList;

public class ElementReaderTest extends PDFNetSample {

	private static OutputListener mOutputListener;

	private static ArrayList<String> mFileList = new ArrayList<>();

    public ElementReaderTest() {
        setTitle(R.string.sample_elementreader_title);
        setDescription(R.string.sample_elementreader_description);
    }

	@Override
	public void run(OutputListener outputListener) {
		super.run(outputListener);
		mOutputListener = outputListener;
		mFileList.clear();
		printHeader(outputListener);

        try    // Extract text data from all pages in the document
        {
            mOutputListener.println("-------------------------------------------------");
            mOutputListener.println("Sample 1 - Extract text data from all pages in the document.");
            mOutputListener.println("Opening the input pdf...");

            PDFDoc doc = new PDFDoc(Utils.getAssetTempFile(INPUT_PATH + "newsletter.pdf").getAbsolutePath());
            doc.initSecurityHandler();

            int pgnum = doc.getPageCount();

            PageIterator itr;
            ElementReader page_reader = new ElementReader();

            for (itr = doc.getPageIterator(); itr.hasNext(); )        //  Read every page
            {
                page_reader.begin(itr.next());
                ProcessElements(page_reader);
                page_reader.end();
            }

            //Close the open document to free up document memory sooner.
            doc.close();
            mOutputListener.println("Done.");
        } catch (Exception e) {
            mOutputListener.printError(e.getStackTrace());
        }

		for (String file : mFileList) {
			addToFileList(file);
		}
		printFooter(outputListener);
	}

    static void ProcessElements(ElementReader reader) throws PDFNetException {
        for (Element element = reader.next(); element != null; element = reader.next())    // Read page contents
        {
			switch (element.getType()) 
			{
				case Element.e_path:                 // Process path data...
				{
					PathData data = element.getPathData();
					byte[] operators = data.getOperators();
					double[] points = data.getPoints();
				}
				break;
				case Element.e_text:                // Process text strings...
				{
					String data = element.getTextString();
					mOutputListener.println(data); 
				}
				break;
				case Element.e_form:                // Process form XObjects
				{
					reader.formBegin();
					ProcessElements(reader);
					reader.end();
				}
				break;
			}
        }
    }

}
close

Free Trial

Get unlimited trial usage of PDFTron SDK to bring accurate, reliable, and fast document processing capabilities to any application or workflow.

Select a platform to get started with your free trial.

Unlimited usage. No email address required.

Join our upcoming webinar to learn about how to collaborate on videos frame by frame directly in your browser

Save your seat
close