Harvesting Web Content into MHTML Archive

using System;
using Rilling.MhtmlLib.Media.Artifacts;
using System.Text;
using System.Net;
using System.Xml;

namespace Rilling.MhtmlLib.Media.Handlers
{
	/// <summary>
	///		A factory that creates an <see cref="HtmlArtifact"/> object.
	/// </summary>
	public class HtmlContentHandler : TextContentHandler
	{
		/// <summary>
		///		Initializes a new <see cref="HtmlArtifact"/>
		///		instance with information from the specified 
		///		<see cref="HttpWebResponse"/> object.
		/// </summary>
		/// <param name="webResponse">
		///		The <see cref="HttpWebResponse"/> used to initialize this instance.
		/// </param>
		/// <returns>
		///		An initialized <see cref="HtmlArtifact"/> instance.
		/// </returns>
		/// <remarks>
		///		Currently there is no validation to ensure the content in the
		///		<see cref="HttpWebResponse"/> is compatible with this artifact.
		/// </remarks>
		public override ArtifactBase
			CreateArtifact(HttpWebResponse webResponse)
		{
			if(webResponse == null) 
				throw(new ArgumentNullException("webResponse"));

			HtmlArtifact artifact = 
				new HtmlArtifact(webResponse.GetResponseStream());

			//
			// Initialize all necessary properties from the web content.
			//
			artifact.ContentType	= webResponse.ContentType.Split(';')[0];
			artifact.Location		= webResponse.ResponseUri;

			string charCode = webResponse.CharacterSet;
			if (charCode != String.Empty)
				artifact.Encoding = Encoding.GetEncoding(charCode);

			return artifact;
		}
	}
}