C++

Extract all HTML Objects from a Web Page

See more MHT / HTML Email Examples

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

#include <CkMht.h>

void ChilkatSample(void)
    {
    bool success = false;

    // This example assumes the Chilkat API to have been previously unlocked.
    // See Global Unlock Sample for sample code.

    CkMht mht;

    // Download a URL into an in-memory MHT web archive contained
    // in a string variable.
    // The following URL is randomly picked and was valid at the time of writing this example:
    const char *mhtDoc = mht.getMHT("https://www.tetonlodge.com/");
    if (mht.get_LastMethodSuccess() != true) {
        std::cout << mht.lastErrorText() << "\r\n";
        return;
    }

    // Extract the HTML and embedded objects:
    const char *unpackDir = "C:/AAWorkarea/mhtTesting/";
    const char *htmlFilename = "lodge.html";
    const char *partsSubdir = "objects";

    // Extract to C:/AAWorkarea/mhtTesting/lodge.html.
    // images and other embedded objects are placed in
    // C:/AAWorkarea/mhtTesting/objects.  Directories are automatically
    // created if they don't already exist.
    success = mht.UnpackMHTString(mhtDoc,unpackDir,htmlFilename,partsSubdir);
    if (success != true) {
        std::cout << mht.lastErrorText() << "\r\n";
    }
    else {
        std::cout << "Unpacked!" << "\r\n";
    }
    }