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.

Download Chilkat C/C++ Libraries for VC++ 9.0 / Win32

Download Chilkat C/C++ Libraries for VC++ 8.0 / Win32

Download Chilkat C/C++ 64-bit Libraries for VC++ 8.0 / x64

Download Chilkat Visual Studio 2005 C/C++ Libs for Windows Mobile, Pocket PC, SmartPhone, WinCE

Download Chilkat C/C++ Libraries for VC++ 7.0 / Win32

Download Chilkat C/C++ Libraries for VC++ 6.0 / Win32

Download Chilkat C/C++ Libraries for VC++ 6.0, Win 95/98/NT4 Compatible

// Needs #include <CkMht.h>

    CkString strOut;

    CkMht mht;

    bool success;
    success = mht.UnlockComponent("30-day trial");
    if (success != true) {
        strOut.append("Mht component unlock failed\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/");
    //  On failure, the mhtDoc will be a zero-length string.
    //  Check the LastErrorText property for error information.

    //  Now extract the HTML and embedded objects:
    const char * unpackDir;
    unpackDir = "c:/temp/";
    const char * htmlFilename;
    htmlFilename = "gopackaging.html";
    const char * partsSubdir;
    partsSubdir = "objects";
    //  Extract to c:/temp/gopackaging.html.
    //  images and other embedded objects are placed in
    //  c:/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());