(Android™) Extract HTML Title, Description, Keywords

This example expands on the "getting started" example by showing how to access the HTML title, description, and keywords within each page spidered. These are the contents of the META tags for keywords, description, and title found in the HTML header.

Chilkat Android™ Downloads Android™ Java Libraries Android C/C++ Libraries

// Important: Don't forget to include the call to System.loadLibrary
// as shown at the bottom of this code sample.
package com.test;

import android.app.Activity;
import com.chilkatsoft.*;

import android.widget.TextView;
import android.os.Bundle;

public class SimpleActivity extends Activity {

  private static final String TAG = "Chilkat";

  // Called when the activity is first created.
  @Override
  public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);

    CkSpider spider = new CkSpider();

    // The spider object crawls a single web site at a time.  As you'll see
    // in later examples, you can collect outbound links and use them to 
    // crawl the web.  For now, we'll simply spider 10 pages of chilkatsoft.com
    spider.Initialize("www.chilkatsoft.com");

    // Add the 1st URL:
    spider.AddUnspidered("http://www.chilkatsoft.com/");

    // Begin crawling the site by calling CrawlNext repeatedly.
    int i;
    for (i = 0; i <= 9; i++) {
        boolean success;
        success = spider.CrawlNext();
        if (success == true) {
            // Show the URL of the page just spidered.
            Log.i(TAG, spider.lastUrl());

            // The HTML META keywords, title, and description are available in these properties:
            Log.i(TAG, spider.lastHtmlTitle());
            Log.i(TAG, spider.lastHtmlDescription());
            Log.i(TAG, spider.lastHtmlKeywords());

            // The HTML is available in the LastHtml property
            }
        else {
            // Did we get an error or are there no more URLs to crawl?
            if (spider.get_NumUnspidered() == 0) {
                Log.i(TAG, "No more URLs to spider");
                }
            else {
                Log.i(TAG, spider.lastErrorText());
                }

            }

        // Sleep 1 second before spidering the next URL.
        spider.SleepMs(1000);
        }


  }

  static {
      System.loadLibrary("chilkat");

      // Note: If the incorrect library name is passed to System.loadLibrary,
      // then you will see the following error message at application startup:
      //"The application <your-application-name> has stopped unexpectedly. Please try again."
  }
}