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 <C_CkMht.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkMht mht;
    const char *mhtDoc;
    const char *unpackDir;
    const char *htmlFilename;
    const char *partsSubdir;

    success = FALSE;

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

    mht = CkMht_Create();

    // 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:
    mhtDoc = CkMht_getMHT(mht,"https://www.tetonlodge.com/");
    if (CkMht_getLastMethodSuccess(mht) != TRUE) {
        printf("%s\n",CkMht_lastErrorText(mht));
        CkMht_Dispose(mht);
        return;
    }

    // Extract the HTML and embedded objects:
    unpackDir = "C:/AAWorkarea/mhtTesting/";
    htmlFilename = "lodge.html";
    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 = CkMht_UnpackMHTString(mht,mhtDoc,unpackDir,htmlFilename,partsSubdir);
    if (success != TRUE) {
        printf("%s\n",CkMht_lastErrorText(mht));
    }
    else {
        printf("Unpacked!\n");
    }



    CkMht_Dispose(mht);

    }