Java

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. Chilkat2 Java

import com.chilkatsoft.chilkat2.ChilkatException;
import com.chilkatsoft.chilkat2.Mht;

public class ChilkatExample {

    public static void main(String[] args) {
        // This example assumes the Chilkat API to have been previously unlocked.
        // See Global Unlock Sample for sample code.

        Mht mht = new 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:
        String mhtDoc;
        try {
            mhtDoc = mht.getMHT("https://www.tetonlodge.com/");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        // Extract the HTML and embedded objects:
        String unpackDir = "C:/AAWorkarea/mhtTesting/";
        String htmlFilename = "lodge.html";
        String 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.
        try {
            mht.unpackMHTString(mhtDoc, unpackDir, htmlFilename, partsSubdir);
            System.out.println("Unpacked!");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
        }
    }
}