I'm trying PhantomJS for the first time, and would like to download a remote site with PHP for SEO purposes.
I've succeed in downloading the HTML content, however the pages are always "Javascript not enabled" fallbacks. From this I can only conclude that the PhantomJS is visiting the sites without Javascript support.. I've posted the script I'm currently using below, which should be pretty standard. Does anyone know a better way of returning remote HTML content with PhantomJS?
phantom.js
var page = require('webpage').create();
var system = require('system');
var url = system.args[1];
page.open(url,
function(status){
if (status !== 'success') {
phantom.exit(1);
return;
} else {
page.evaluate(
function() {
return document.documentElement.outerHTML;
},
function(result){
console.log(result);
});
}
phantom.exit();
});
index.php
$url = escapeshellarg('<some url to test>');
$script = "phantom.js";
$contents = shell_exec("/usr/local/bin/phantomjs $script $url");