Parsing html to pdf with iText, image base64 [duplicate]

Answer 1

It's possible to replace the built-in tags processors of iText(Sharp). Here is the C# code with custom image tag processor which supports base64 images too. It's easy to convert it to java (base libraries iText and iTextSharp have the same API).

using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.html;
using iTextSharp.text.html.simpleparser;
using iTextSharp.text.pdf;

namespace CustomHtmlWorkerTag
{
    /// 

    /// Our custom HTML Tag to add an IElement.
    /// 
    public class CustomImageHTMLTagProcessor : IHTMLTagProcessor
    {
        /// 

        /// Tells the HTMLWorker what to do when a close tag is encountered.
        /// 
        public void EndElement(HTMLWorker worker, string tag)
        {
        }

        /// 

        /// Tells the HTMLWorker what to do when an open tag is encountered.
        /// 
        public void StartElement(HTMLWorker worker, string tag, IDictionary attrs)
        {
            Image image;
            var src = attrs["src"];

            if (src.StartsWith("data:image/"))
            {
                // data:[][;charset=][;base64],
                var base64Data = src.Substring(src.IndexOf(",") + 1);
                var imagedata = Convert.FromBase64String(base64Data);
                image = Image.GetInstance(imagedata);
            }
            else
            {
                image = Image.GetInstance(src);
            }

            worker.UpdateChain(tag, attrs);
            worker.ProcessImage(image, attrs);
            worker.UpdateChain(tag);
        }
    }

    class Program
    {
        static void Main(string[] args)
        {
            using (var pdfDoc = new Document(PageSize.A4))
            {
                PdfWriter.GetInstance(pdfDoc, new FileStream("Test.pdf", FileMode.Create));
                pdfDoc.Open();

                FontFactory.Register("c:\\windows\\fonts\\tahoma.ttf");

                var tags = new HTMLTagProcessors();
                // Replace the built-in image processor
                tags[HtmlTags.IMG] = new CustomImageHTMLTagProcessor();

                var html = "";

                var styles = new StyleSheet();
                styles.LoadTagStyle(HtmlTags.BODY, HtmlTags.FONTFAMILY, "tahoma");
                styles.LoadTagStyle(HtmlTags.BODY, HtmlTags.ENCODING, "Identity-H");

                PdfPCell pdfCell = new PdfPCell { Border = 0 };
                pdfCell.RunDirection = PdfWriter.RUN_DIRECTION_LTR;

                using (var reader = new StringReader(html))
                {
                    var parsedHtmlElements = HTMLWorker.ParseToList(reader, styles, tags, null);

                    foreach (var htmlElement in parsedHtmlElements)
                    {
                        pdfCell.AddElement(htmlElement);
                    }
                }

                var table1 = new PdfPTable(1);
                table1.AddCell(pdfCell);
                pdfDoc.Add(table1);
            }

            Process.Start("Test.pdf");
        }
    }
}