Node.js

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. Node.js

NODEJS_PRELUDE

function chilkatExample() {

    var success = false;

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

    var mht = new chilkat.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:
    var mhtDoc = mht.GetMHT("https://www.tetonlodge.com/");
    if (mht.LastMethodSuccess !== true) {
        console.log(mht.LastErrorText);
        return;
    }

    //  Extract the HTML and embedded objects:
    var unpackDir = "C:/AAWorkarea/mhtTesting/";
    var htmlFilename = "lodge.html";
    var 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) {
        console.log(mht.LastErrorText);
    }
    else {
        console.log("Unpacked!");
    }


}

chilkatExample();