Unicode C

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. Unicode C

#include <C_CkGlobalW.h>
#include <C_CkHttpW.h>
#include <C_CkHtmlToXmlW.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkGlobalW glob;
    HCkHttpW http;
    const wchar_t *html;
    HCkHtmlToXmlW htmlToXml;
    const wchar_t *xml;

    success = FALSE;

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

    // Any string argument automatically begins the 30-day trial.
    glob = CkGlobalW_Create();
    success = CkGlobalW_UnlockBundle(glob,L"30-day trial");
    if (success != TRUE) {
        wprintf(L"%s\n",CkGlobalW_lastErrorText(glob));
        CkGlobalW_Dispose(glob);
        return;
    }

    http = CkHttpW_Create();

    html = CkHttpW_quickGetStr(http,L"http://www.intel.com/");
    if (CkHttpW_getLastMethodSuccess(http) != TRUE) {
        wprintf(L"%s\n",CkHttpW_lastErrorText(http));
        CkGlobalW_Dispose(glob);
        CkHttpW_Dispose(http);
        return;
    }

    htmlToXml = CkHtmlToXmlW_Create();

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

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

    // Convert to XML:

    xml = CkHtmlToXmlW_toXml(htmlToXml);

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

    wprintf(L"Finished.\n");


    CkGlobalW_Dispose(glob);
    CkHttpW_Dispose(http);
    CkHtmlToXmlW_Dispose(htmlToXml);

    }