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

#include <C_CkHttp.h>
#include <C_CkHtmlToXml.h>
#include <C_CkXml.h>

void ChilkatSample(void)
    {
    HCkHttp http;
    BOOL success;
    const char * html;
    HCkHtmlToXml htmlToXml;
    HCkXml xml;
    HCkXml formRoot;
    HCkXml xmlTemp;
    HCkXml xmlNode;

    http = CkHttp_Create();

    //  Any string unlocks the component for the 1st 30-days.
    success = CkHttp_UnlockComponent(http,"Anything for 30-day trial");
    if (success != TRUE) {
        printf("%s\n",CkHttp_lastErrorText(http));
        return;
    }

    //  Send the HTTP GET and return the content in a string.

    html = CkHttp_quickGetStr(http,"http://www.nature.com/register/");

    //  Convert the HTML to XML for parsing...
    htmlToXml = CkHtmlToXml_Create();

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

    success = CkHtmlToXml_UnlockComponent(htmlToXml,"30-day trial");
    if (success != TRUE) {
        printf("HtmlToXml component unlock failed\n");
        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...
    CkHtmlToXml_putXmlCharset(htmlToXml,"utf-8");

    //  Set the HTML:
    CkHtmlToXml_putHtml(htmlToXml,html);

    //  Convert and load into an XML object:
    xml = CkXml_Create();
    CkXml_LoadXml(xml,CkHtmlToXml_toXml(htmlToXml));

    success = CkXml_SaveXml(xml,"out.xml");
    if (success != TRUE) {
        printf("%s\n",CkXml_lastErrorText(xml));
        return;
    }

    //  Find the first form tag and navigate to it:

    formRoot = CkXml_SearchForTag(xml,0,"form");

    if (formRoot == 0 ) {
        printf("No HTML form found!\n");
        return;
    }

    //  Show the form's name, method, and action:
    printf("Form Name: %s\n",CkXml_getAttrValue(formRoot,"name"));
    printf("Form Method: %s\n",CkXml_getAttrValue(formRoot,"method"));
    printf("Form Action: %s\n",CkXml_getAttrValue(formRoot,"action"));
    printf("----\n");

    //  Iterate over "input" tags within the form:

    xmlNode = CkXml_SearchForTag(formRoot,0,"input");
    while ((!(xmlNode == 0 ))) {

        //  print the input field's name, type, and current value:
        //  an empty input type indicates the default "text" type
        printf("Input Name: %s\n",CkXml_getAttrValue(xmlNode,"name"));
        printf("Input Type: %s\n",CkXml_getAttrValue(xmlNode,"type"));
        printf("Current Value: %s\n",CkXml_getAttrValue(xmlNode,"value"));
        printf("----\n");

        xmlTemp = xmlNode;
        xmlNode = CkXml_SearchForTag(formRoot,xmlNode,"input");
        CkXml_Dispose(xmlTemp);
    }

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

        printf("Select Name: %s\n",CkXml_getAttrValue(xmlNode,"name"));

        xmlTemp = xmlNode;
        xmlNode = CkXml_SearchForTag(formRoot,xmlNode,"select");
        CkXml_Dispose(xmlTemp);
    }

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

        printf("TextArea Name: %s\n",CkXml_getAttrValue(xmlNode,"name"));

        xmlTemp = xmlNode;
        xmlNode = CkXml_SearchForTag(formRoot,xmlNode,"textarea");
        CkXml_Dispose(xmlTemp);
    }

    CkXml_Dispose(formRoot);

    CkHttp_Dispose(http);
    CkHtmlToXml_Dispose(htmlToXml);
    CkXml_Dispose(xml);

    }