Extract all HTML Objects from a Web Page

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc.

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 <CkMht.h>

    CkString strOut;

    CkMht mht;

    bool success;
    success = mht.UnlockComponent("Anything for 30-day trial");
    if (success != true) {
        strOut.append(mht.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Download a URL into an in-memory MHT web archive contained
    //  in a string variable:
    const char * mhtDoc;
    mhtDoc = mht.getMHT("http://www.gopackaging.com/");
    if (mhtDoc == 0 ) {
        strOut.append(mht.lastErrorText());
        strOut.append("\r\n");
        SetDlgItemText(IDC_EDIT1,strOut.getUnicode());
        return;
    }

    //  Now extract the HTML and embedded objects:
    const char * unpackDir;
    unpackDir = "/Users/chilkat/temp/";
    const char * htmlFilename;
    htmlFilename = "gopackaging.html";
    const char * partsSubdir;
    partsSubdir = "objects";
    //  Extract to /Users/chilkat/temp/gopackaging.html.
    //  images and other embedded objects are placed in
    //  /Users/chilkat/temp/objects.  Directories are automatically
    //  created if they don't already exist.
    success = mht.UnpackMHTString(mhtDoc,unpackDir,htmlFilename,partsSubdir);
    if (success != true) {
        strOut.append(mht.lastErrorText());
        strOut.append("\r\n");
    }
    else {
        strOut.append("Unpacked!\r\n");
    }



    SetDlgItemText(IDC_EDIT1,strOut.getUnicode());