Download HTML from URL and Convert to XML

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

Downloads:

MS Windows Visual C/C++ Libraries

Linux/CentOS C/C++ Libraries

MAC OS X C/C++ Libraries

Solaris C/C++ Libraries

C++ Builder Libraries

// Needs #include <CkHttp.h>
// Needs #include <CkHtmlToXml.h>

    CkString strOut;

    //  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 existing Chilkat components.  Also, new-version upgrades are always free.

    CkHttp http;

    //  Any string argument automatically begins the 30-day trial.
    bool success;
    success = http.UnlockComponent("30-day trial");
    if (success != true) {
        strOut.append(http.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    const char * html;
    html = http.quickGetStr("http://www.intel.com/");
    if (html == 0 ) {
        strOut.append(http.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    CkHtmlToXml htmlToXml;

    //  Any string argument automatically begins the 30-day trial.
    success = htmlToXml.UnlockComponent("30-day trial");
    if (success != true) {
        strOut.append(htmlToXml.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

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

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

    //  Convert to XML:
    const char * 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","utf-8");

    strOut.append("Finished.\r\n");

    SetDlgItemText(IDC_EDIT1,strOut.getUnicode());