Download HTML from URL and Convert to XML

Downloads an HTML page from a URL and converts it to XML.

Download Chilkat Java Library

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[])
  {
    //  Note: This example uses two Chilkat products: Chilkat HTTP
    //  and Chilkat HTML-to-XML.  The "Chilkat Bundle" can be licensed
    //  at a price that is less than purchasing each product individually.
    //  The "Chilkat Bundle" provides licenses to all Chilkat components.  Also, new-version upgrades are always free.

    CkHttp http = new CkHttp();

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

    String html;
    html = http.quickGetStr("http://www.intel.com/");
    if (html == null ) {
        System.out.println(http.lastErrorText());
        return;
    }

    CkHtmlToXml htmlToXml = new CkHtmlToXml();

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

    //  Indicate the charset of the output XML we'll want.
    htmlToXml.put_XmlCharset("iso-8859-1");

    //  Set the HTML:
    htmlToXml.put_Html(html);

    //  Convert to XML:
    String xml;
    xml = htmlToXml.toXml();

    //  Save the XML to a file.
    //  Make sure your charset here matches the charset
    //  used for the XmlCharset property.
    htmlToXml.WriteStringToFile(xml,"out.xml","iso-8859-1");

    System.out.println("Finished.");

  }
}