Converti Html in Docx in c#

Converti Html in Docx in c#

La mia soluzione utilizza Html2OpenXml insieme a DocumentFormat.OpenXml (il pacchetto NuGet per Html2OpenXml è qui) per fornire una soluzione elegante per ASP.NET MVC.

WordHelper.cs

public static class WordHelper
{
    public static byte[] HtmlToWord(String html)
    {
        const string filename = "test.docx";
        if (File.Exists(filename)) File.Delete(filename);

        using (MemoryStream generatedDocument = new MemoryStream())
        {
            using (WordprocessingDocument package = WordprocessingDocument.Create(
                   generatedDocument, WordprocessingDocumentType.Document))
            {
                MainDocumentPart mainPart = package.MainDocumentPart;
                if (mainPart == null)
                {
                    mainPart = package.AddMainDocumentPart();
                    new Document(new Body()).Save(mainPart);
                }

                HtmlConverter converter = new HtmlConverter(mainPart);
                Body body = mainPart.Document.Body;

                var paragraphs = converter.Parse(html);
                for (int i = 0; i < paragraphs.Count; i++)
                {
                    body.Append(paragraphs[i]);
                }

                mainPart.Document.Save();
            }

            return generatedDocument.ToArray();
        }
    }
}

Titolare

    [HttpPost]
    [ValidateInput(false)]
    public FileResult Demo(CkEditorViewModel viewModel)
    {
        return File(WordHelper.HtmlToWord(viewModel.CkEditorContent),
          "application/vnd.openxmlformats-officedocument.wordprocessingml.document");
    }

Sto usando CKEditor per generare HTML per questo esempio.

Di seguito fa la stessa cosa del codice Luis, ma solo un po' più leggibile e applicato a un'applicazione ASP.NET MVC:

var word = new Microsoft.Office.Interop.Word.Application();
word.Visible = false;

var filePath = Server.MapPath("~/MyFiles/Html2PdfTest.html");
var savePathPdf = Server.MapPath("~/MyFiles/Html2PdfTest.pdf");
var wordDoc = word.Documents.Open(FileName: filePath, ReadOnly: false);
wordDoc.SaveAs2(FileName: savePathPdf, FileFormat: WdSaveFormat.wdFormatPDF);

puoi anche salvare in altri formati come docx come questo:

var savePathDocx = Server.MapPath("~/MyFiles/Html2PdfTest.docx");
var wordDoc = word.Documents.Open(FileName: filePath, ReadOnly: false);
wordDoc.SaveAs2(FileName: savePathDocx, FileFormat: WdSaveFormat.wdFormatXMLDocument);

Usare quel codice per convertire

Microsoft.Office.Interop.Word.Application word = 
    new Microsoft.Office.Interop.Word.Application();
Microsoft.Office.Interop.Word.Document wordDoc = 
    new Microsoft.Office.Interop.Word.Document();
Object oMissing = System.Reflection.Missing.Value;
wordDoc = word.Documents.Add(ref oMissing, ref oMissing, ref oMissing, ref oMissing);
word.Visible = false;
Object filepath = "c:\\page.html";
Object confirmconversion = System.Reflection.Missing.Value;
Object readOnly = false;
Object saveto = "c:\\doc.pdf";
Object oallowsubstitution = System.Reflection.Missing.Value;

wordDoc = word.Documents.Open(ref filepath, ref confirmconversion, 
    ref readOnly, ref oMissing,
    ref oMissing, ref oMissing, ref oMissing, ref oMissing,
    ref oMissing, ref oMissing, ref oMissing, ref oMissing,
    ref oMissing, ref oMissing, ref oMissing, ref oMissing);
 object fileFormat = WdSaveFormat.wdFormatPDF;
 wordDoc.SaveAs(ref saveto, ref fileFormat, ref oMissing, ref oMissing, ref oMissing,
     ref oMissing, ref oMissing, ref oMissing, ref oMissing, ref oMissing,
     ref oMissing, ref oMissing, ref oMissing, ref oallowsubstitution, ref oMissing,
     ref oMissing);