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++ Libraries for VC++ 8.0 / Win32

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

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

#include <CkMht.h>
#include <CkString.h>

void ChilkatSample(void)
    {
    CkMht mht;

    bool success;
    success = mht.UnlockComponent("30-day trial");
    if (success != true) {
        printf("Mht component unlock failed\n");
        return;
    }

    // Download a URL into an in-memory MHT web archive contained
    // in a string variable:
    CkString 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:
    CkString unpackDir;
    unpackDir = "c:/temp/";
    CkString htmlFilename;
    htmlFilename = "gopackaging.html";
    CkString 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) {
        printf("%s\n",mht.lastErrorText());
    }
    else {
        printf("Unpacked!\n");
    }


    }