Extract HTML Form Information

Download an HTML page, parse the HTML, and extract information for the 1st form on the page.

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

FreeBSD C++ Libraries

HP-UX C++ Libraries

BlackBerry QNX C++ Libraries

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

    CkString strOut;

    CkHttp http;

    bool success;

    //  Any string unlocks the component for the 1st 30-days.
    success = http.UnlockComponent("Anything for 30-day trial");
    if (success != true) {
        strOut.append(http.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Send the HTTP GET and return the content in a string.
    const char * html;
    html = http.quickGetStr("http://www.nature.com/register/");

    //  Convert the HTML to XML for parsing...
    CkHtmlToXml htmlToXml;

    //  Any string argument automatically begins the 30-day trial.

    success = htmlToXml.UnlockComponent("30-day trial");
    if (success != true) {
        strOut.append("HtmlToXml component unlock failed\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Indicate the charset of the output XML we'll want.
    //  The charset of the original HTML page can be anything.
    //  Chilkat will convert and handle it properly...
    htmlToXml.put_XmlCharset("utf-8");

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

    //  Convert and load into an XML object:
    CkXml xml;
    xml.LoadXml(htmlToXml.toXml());

    success = xml.SaveXml("out.xml");
    if (success != true) {
        strOut.append(xml.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Find the first form tag and navigate to it:
    CkXml *formRoot = 0;
    formRoot = xml.SearchForTag(0,"form");

    if (formRoot == 0 ) {
        strOut.append("No HTML form found!\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Show the form's name, method, and action:
    strOut.append("Form Name: ");
    strOut.append(formRoot->getAttrValue("name"));
    strOut.append("\r\n");
    strOut.append("Form Method: ");
    strOut.append(formRoot->getAttrValue("method"));
    strOut.append("\r\n");
    strOut.append("Form Action: ");
    strOut.append(formRoot->getAttrValue("action"));
    strOut.append("\r\n");
    strOut.append("----");
    strOut.append("\r\n");

    //  Iterate over "input" tags within the form:
    CkXml *xmlTemp = 0;
    CkXml *xmlNode = 0;

    xmlNode = formRoot->SearchForTag(0,"input");
    while ((!(xmlNode == 0 ))) {

        //  print the input field's name, type, and current value:
        //  an empty input type indicates the default "text" type
        strOut.append("Input Name: ");
        strOut.append(xmlNode->getAttrValue("name"));
        strOut.append("\r\n");
        strOut.append("Input Type: ");
        strOut.append(xmlNode->getAttrValue("type"));
        strOut.append("\r\n");
        strOut.append("Current Value: ");
        strOut.append(xmlNode->getAttrValue("value"));
        strOut.append("\r\n");
        strOut.append("----");
        strOut.append("\r\n");

        xmlTemp = xmlNode;
        xmlNode = formRoot->SearchForTag(*xmlNode,"input");
        delete xmlTemp;
    }

    //  Iterate over "select" tags within the form:
    xmlNode = formRoot->SearchForTag(0,"select");
    while ((!(xmlNode == 0 ))) {

        strOut.append("Select Name: ");
        strOut.append(xmlNode->getAttrValue("name"));
        strOut.append("\r\n");

        xmlTemp = xmlNode;
        xmlNode = formRoot->SearchForTag(*xmlNode,"select");
        delete xmlTemp;
    }

    //  Iterate over "textarea" tags within the form:
    xmlNode = formRoot->SearchForTag(0,"textarea");
    while ((!(xmlNode == 0 ))) {

        strOut.append("TextArea Name: ");
        strOut.append(xmlNode->getAttrValue("name"));
        strOut.append("\r\n");

        xmlTemp = xmlNode;
        xmlNode = formRoot->SearchForTag(*xmlNode,"textarea");
        delete xmlTemp;
    }

    delete formRoot;

    SetDlgItemText(IDC_EDIT1,strOut.getUnicode());