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 Java Library

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    CkMht mht = new CkMht();

    boolean success;
    success = mht.UnlockComponent("30-day trial");
    if (success != true) {
        System.out.println("Mht component unlock failed");
        return;
    }

    // Download a URL into an in-memory MHT web archive contained
    // in a string variable:
    String 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:
    String unpackDir;
    unpackDir = "c:/temp/";
    String htmlFilename;
    htmlFilename = "gopackaging.html";
    String 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) {
        System.out.println(mht.lastErrorText());
    }
    else {
        System.out.println("Unpacked!");
    }


  }
}