(MFC) CanonicalizeUrl

The CanonicalizeUrl method is a utility function that canonicalizes a URL into a standard form to avoid duplicates. For example, "http://www.chilkatsoft.com/" and "http://www.chilkatsoft.com/default.asp" are the same URL.

Chilkat C/C++ Library Downloads MS Visual C/C++ Libs

See Also: Using MFC CString in Chilkat

#include <CkSpider.h>

void ChilkatSample(void)
    {
    CkString strOut;

    CkSpider spider;

    // Does a DNS lookup to find the default domain, which may or may not include the "www." depending on the DNS results.
    // Also domain names are converted to lowercase:
    strOut.append(spider.canonicalizeUrl("http://www.ChilkatSoft.com/"));
    strOut.append("\r\n");

    // CanonicalizeUrl will drop the HTML fragment:
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/purchase2.asp#buyZip"));
    strOut.append("\r\n");

    // If a username/password is in the URL, it gets dropped:
    strOut.append(spider.canonicalizeUrl("http://username:password@www.chilkatsoft.com/purchase2.asp#buyZip"));
    strOut.append("\r\n");

    // Port 80 and 443 are dropped:
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com:80/purchase2.asp"));
    strOut.append("\r\n");
    strOut.append(spider.canonicalizeUrl("https://www.paypal.com:443/"));
    strOut.append("\r\n");

    // Removes default pages:
    // default.asp, index.html, index.htm, default.html, index.htm, default.htm
    // index.php, index.asp, default.php, .cfm, .aspx, ,php3, .pl, .cgi, .txt, .shtml, .phtml
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/index.asp"));
    strOut.append("\r\n");
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/index.asp"));
    strOut.append("\r\n");
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/index.php"));
    strOut.append("\r\n");
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/index.pl"));
    strOut.append("\r\n");
    strOut.append(spider.canonicalizeUrl("http://www.chilkatsoft.com/index.htm"));
    strOut.append("\r\n");

    // Output:
    // http://chilkatsoft.com/
    // http://chilkatsoft.com/purchase2.asp
    // http://chilkatsoft.com/purchase2.asp
    // http://chilkatsoft.com/purchase2.asp
    // https://www.paypal.com/
    // http://chilkatsoft.com/
    // http://chilkatsoft.com/
    // http://chilkatsoft.com/
    // http://chilkatsoft.com/
    // http://chilkatsoft.com


    SetDlgItemText(IDC_EDIT1,strOut.getUnicode());

    }