html to openxml
How to start ?
Create a new console application. Add a reference to DocumentFormat.OpenXml.dll (shipped with the OpenXml SDK 2.0).
Add an html file and fill it with:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html>
<head>
<title></title>
</head>
<body>
Looks how cool is <font size="x-large"><b>Open Xml</b></font>.
Now with <font color="red"><u>HtmlToOpenXml</u></font>, it nevers been so easy to convert html.
<p>
If you like it, add me a rating on <a href="http://notesforhtml2openxml.codeplex.com">codeplex</a>
</p>
<hr>
</body>
</html>
Add a Resources.resx component and add your html file inside it.
In Program.cs, add these lines of code:
using System.IO;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;
using NotesFor.HtmlToOpenXml;
...
static void Main(string[] args)
{
const string filename = "test.docx";
string html = Properties.Resources.DemoHtml;
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();
}
File.WriteAllBytes(filename, generatedDocument.ToArray());
}
System.Diagnostics.Process.Start(filename);
}
