If the pages are well-formed XHTML then it is possible to use XmlReader
(in .NET 2.0/3.0) or XmlTextReader (in .NET 1.x) to parse the XHTML
documents. You can also use the other XML APIs .NET provides so using
XPathNavigator and/or XmlDocument might offer more comfort than XmlReader.

Here is an example using XmlReader that prints out all heading elements
(h1 .. h6 elements) assuming they have no child elements:

    static public void PrintHeadings (string path) {
      XmlReaderSettings settings = new XmlReaderSettings();
      settings.ProhibitDtd = false;
      using (XmlReader xmlReader = XmlReader.Create(path, settings)) {
        while (xmlReader.Read()) {
          if (xmlReader.NodeType == XmlNodeType.Element &&
xmlReader.NamespaceURI == "http://www.w3.org/1999/xhtml") {
            switch (xmlReader.LocalName) {
              case "h1":
              case "h2":
              case "h3":
              case "h4":
              case "h5":
              case "h6":
                Console.Out.WriteLine(
"{0} heading has InnerText: \"{1}\".", xmlReader.LocalName,
xmlReader.ReadString());
                break;
            }
          }
        }
      }

      PrintHeasdings("doc.xhtml");
    }