PhantomJS

Use page.evaluate() method to evaluate the page.

To extract title tag use document.title.

status can be: status='success | fail'

 

/**
 * Get HTML content from URL
 * Simple JS DOM usage document.title
 */

var page = require('webpage').create(),
    url = 'http://www.mikosoft.info';

page.open(url, function(status) {
  console.log(status);
      if(status === 'success') {
          
          var title = page.evaluate(function() {
            return document.title;
          });
 
          console.log('Page title is: '+title);
      }
      else console.log('404 Not found: '+url);
      
      
 
  phantom.exit();
});

 

Notice that we reached title with simple JS DOM document.title .

If we want to apply jQuery selectors use

• page.includeJS() to get external file:  http://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js
• page.InjectJs() to get local file: ./assets/js/jquery/1.11.1/jquery.min.js

 

See examples:

 

Get title tag - JS DOM: 01get_titletag_dom.js

Get title tag - jQuery loaded from Google CDN by IncludeJs: 02get_titletag_jquery_ggl.js

Get head content - jQuery loaded from local file by InjectJs: 02get_titletag_jquery_loc.js

 

 

 

To grab the whole web page HTML use: document.documentElement.outerHTML

 var page = require('webpage').create(),
    url = 'http://www.mikosoft.info';

page.open(url, function(status) {
  console.log(status);
      if(status === 'success') {
          
          var doc = page.evaluate(function() {
            return document.documentElement.outerHTML;
          });
 
          console.log("URL code is: \n\n" +doc);
      }
      else console.log('404 Not found: '+url);
      
      
 
  phantom.exit();
});