Node.js

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. Node.js

NODEJS_PRELUDE

function chilkatExample() {

    var success = false;

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

    //  Any string argument automatically begins the 30-day trial.
    var glob = new chilkat.Global();
    success = glob.UnlockBundle("30-day trial");
    if (success !== true) {
        console.log(glob.LastErrorText);
        return;
    }

    var http = new chilkat.Http();

    var html;
    html = http.QuickGetStr("http://www.intel.com/");
    if (http.LastMethodSuccess !== true) {
        console.log(http.LastErrorText);
        return;
    }

    var htmlToXml = new chilkat.HtmlToXml();

    //  Indicate the charset of the output XML we'll want.
    htmlToXml.XmlCharset = "utf-8";

    //  Set the HTML:
    htmlToXml.Html = html;

    //  Convert to XML:
    var xml;
    xml = htmlToXml.ToXml();

    //  Save the XML to a file.
    //  Make sure your charset here matches the charset
    //  used for the XmlCharset property.
    success = htmlToXml.WriteStringToFile(xml,"qa_output/out.xml","utf-8");

    console.log("Finished.");

}

chilkatExample();