Convert HTML to XML with Auto-Correction

Simple HTML to XML conversion. Demonstrates how the HTML is auto-corrected to create well-formed XML. In this example, the closing

is missing. Also, text is encapsulated in nodes with the intent to make it easy for programs to identify and extract the text parts.

Chilkat Java Library Downloads for Windows, Linux, and MAC OS X

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    CkHtmlToXml htmlToXml = new CkHtmlToXml();

    //  Any string argument automatically begins the 30-day trial.
    boolean success;
    success = htmlToXml.UnlockComponent("30-day trial");
    if (success != true) {
        System.out.println(htmlToXml.lastErrorText());
        return;
    }

    //  Indicate the charset of the output XML we'll want.
    htmlToXml.put_XmlCharset("utf-8");

    //  Set the HTML:
    htmlToXml.put_Html("<html><body><p>This is a test <a href=\"http://www.chilkatsoft.com/\">Chilkat Software</a></body></html>");

    //  Get the XML:
    System.out.println(htmlToXml.toXml());

    //  This is the output:
    //  <?xml version="1.0" encoding="utf-8" ?>
    // 
    //  <root>
    //      <html>
    //          <body>
    //              <p>
    //                  <text>This is a test </text>
    //                  <a href="http://www.chilkatsoft.com/">
    //                      <text>Chilkat Software</text>
    //                  </a>
    //              </p>
    //          </body>
    //      </html>
    //  </root>

  }
}