Java

Download HTML from URL and Convert to XML

See more HTML-to-XML/Text Examples

Downloads an HTML page from a URL and converts it to XML. Chilkat2 Java

import com.chilkatsoft.chilkat2.ChilkatException;
import com.chilkatsoft.chilkat2.Global;
import com.chilkatsoft.chilkat2.HtmlToXml;
import com.chilkatsoft.chilkat2.Http;

public class ChilkatExample {

    public static void main(String[] args) {
        boolean success = false;

        // Note: This example requires the Chilkat Bundle license.

        // Any string argument automatically begins the 30-day trial.
        Global glob = new Global();
        try {
            glob.unlockBundle("30-day trial");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        Http http = new Http();

        String html = "";
        try {
            html = http.quickGetStr("http://www.intel.com/");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        HtmlToXml htmlToXml = new HtmlToXml();

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

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

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

        // Save the XML to a file.
        // Make sure your charset here matches the charset
        // used for the XmlCharset property.
ERROR: Method not in Chilkat2 Java: HtmlToXml.WriteStringToFile
        success = htmlToXml.ERROR();

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