summary

How to convert HTML file to PDF file?Some recruitment online resume into doc file, can not be used directly, this caused great trouble, then it also has a format, that is HTML format. Export the file to HTML format, and then convert it to PDF file, so that it can be used directly. Usually in the project is also a lot of such requirements, need to convert the content into PDF file.

Now let’s take a look at how to convert HTML to PDF using itextsharp.

code implementation

1. Nuget installs itextsharp.

using iTextSharp.text;
using iTextSharp.text.pdf;

2. Convert HTML document to PDF.

  /// <summary>
        /// Switch Html Document to pdf
        /// </summary>
        /// <param name="htmlText"></param>
        /// <returns></returns>
        public byte[] ConvertHtmlTextToPDF(string htmlText)
        {
            if (string.IsNullOrEmpty(htmlText))
                return null;
            //to avoid when the htmlText without any html tag tag plain text, to PDF will hang, so all with <p> tag
            htmlText = "<p>" + htmlText + "</p>";
            using (var outputStream = new MemoryStream())
            {
                byte[] data = Encoding.UTF8.GetBytes(htmlText);
                var msInput = new MemoryStream(data);
                var doc = new Document();//pdf file，default A4 formate
                var writer = PdfWriter.GetInstance(doc, outputStream);
                doc.Open();
                iTextSharp.tool.xml.XMLWorkerHelper.GetInstance().ParseXHtml(writer, doc, msInput, null, Encoding.UTF8, new UnicodeFontFactory());
                var pdfDest = new PdfDestination(PdfDestination.XYZ, 0, doc.PageSize.Height, 1f);
                var action = PdfAction.GotoLocalPage(1, pdfDest, writer);
                writer.SetOpenAction(action);
                doc.Close();
                msInput.Close();
                outputStream.Close();
                return outputStream.ToArray();
            }
        }

3. Unicode font support.

   /// <summary>
        /// Unicode font support
        /// </summary>
        public class UnicodeFontFactory : FontFactoryImp
        {
            public override Font GetFont(string fontname, string encoding, bool embedded, float size, int style, BaseColor color, bool cached)
            {
                //var chineseFontPath = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Fonts), "msyh.ttc,0");
                //BaseFont baseFont = BaseFont.CreateFont(@"c:\Windows\Fonts\simsun.ttc,0", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);
                BaseFont baseFont = BaseFont.CreateFont(@"c:\Windows\Fonts\SIMHEI.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);
                //var baseFont = BaseFont.CreateFont(chineseFontPath, BaseFont.IDENTITY_H, BaseFont.EMBEDDED);
                return new Font(baseFont, size, style, color);
            }
        }

4. Call build.

   string content = temp.Content;
            foreach (var dict in dicts)
            {
                content = content.Replace("{{" + dict.Key + "}}", dict.Value);
            }
            var path = _esignInfo.Value.ContractPath;
            //if (entity.ContractType == ContractType.First)
            //{
            //    path += "/" + appId + "/Agreements";
            //}
            entity.OriginalFileUrl = _pdfHelper.WritePdfFile(content, contractNo, path, "PDF");
            bool isSucc = !String.IsNullOrEmpty(entity.OriginalFileUrl);