[C#] OpenXML: Convert Microsoft Word File to HTML File
// download and install "OpenXML SDK 2.5": http://www.microsoft.com/en-us/download/details.aspx?id=30425
// download, unzip and build "PowerTools for Open XML": http://powertools.codeplex.com/
// add reference: DocumentFormat.OpenXML, Windows.Base, OpenXmlPowerTools
//
..
using DocumentFormat.OpenXml.Office2013.Word;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;
using OpenXmlPowerTools;
using System.Xml.Linq;
..
byte[] byteArray = File.ReadAllBytes(@"e:\a.docx");
using (MemoryStream memoryStream = new MemoryStream())
{
memoryStream.Write(byteArray, 0, byteArray.Length);
using (WordprocessingDocument doc =
WordprocessingDocument.Open(memoryStream, true))
{
HtmlConverterSettings settings = new HtmlConverterSettings()
{
PageTitle = "My Page Title"
};
XElement html = HtmlConverter.ConvertToHtml(doc, settings);
File.WriteAllText(@"e:\Test.html", html.ToStringNewLineOnAttributes());
}
}