stawecki/webkitscrape.html

## webkitscrape.html
<script>

var socket;
var seqNo = 1;
var seqCallback = [];
var remoteOnChange;
var remoteOnLoad;
var remoteURL;

function remoteEval(scriptString,callback) {
	seqCallback[seqNo] = callback;
	socket.send('{"seq":'+seqNo+',"domain":"Runtime","command":"evaluate","arguments":{"expression":"'+
				scriptString.replace(/[\"]/g,'\\"')
				+'","objectGroup":"console","includeCommandLineAPI":false}}');
	seqNo++;
}

remoteOnChange = function(result) { remoteURL = result.url; };


function init() {

	var host = "ws://localhost:9222/devtools/page/5"; // Set page number!
	socket = new WebSocket(host);
	socket.onopen = function(msg){ run(); };
	socket.onmessage = function(msg){
		console.log('onMessage: '+msg.data);

		try
		  {
			var responseObj = JSON.parse(msg.data);
			if (responseObj.seq > 0) {
				if (seqCallback[responseObj.seq] != undefined)
					{
						seqCallback[responseObj.seq](responseObj.body.result.description);
					}
			}
			if (responseObj.event == "inspectedURLChanged" && remoteOnChange != undefined)
				{
					remoteOnChange(responseObj.body);
				}

			if (responseObj.event == "loadEventFired" && remoteOnLoad != undefined)
				{
					remoteOnLoad();
				}
		  } catch(err) {}
		}
}

	function run(){
		remoteOnLoad = function(result) {

				// We might've ended up on the login page, so let's log in!
				if (remoteURL.indexOf("ServiceLogin") > 0 )
					remoteEval( " document.getElementById('Email').value = 'username'; "+
								" document.getElementById('Passwd').value = 'password'; "+
								" document.getElementsByTagName('form')[0].submit(); "
								, function(result) { alert(result); } );

				// We're home!
				if (remoteURL.indexOf("mail.google.com/mail/") > 0 )
					remoteEval( " try { document.getElementById('canvas_frame').contentWindow.document."+
								"getElementsByClassName( 'md' )[0].innerText } catch(e) { -1 }"
								, function(result) {  									  // Waiting for AJAX:
									if (result == -1) { setTimeout(remoteOnLoad,2000); } // Try again in 2 sec.
									else { alert(result); } } ); // This should return scraped information
																// about your data usage on gmail! :D
			} ;

		// This happenes first:
		remoteEval(" location.href = 'http://gmail.com' ");	 //Let's go to Gmail!
		} ;


</script>
<body onload="init()">

<textarea id="remoteText" cols="100" ></textarea><input type="button" value="Remote eval"
	onclick=" remoteEval( document.getElementById('remoteText').value , function(result) { alert(result); } ); " />

</body>
	<script>

	var socket;
	var seqNo = 1;
	var seqCallback = [];
	var remoteOnChange;
	var remoteOnLoad;
	var remoteURL;

	function remoteEval(scriptString,callback) {
	seqCallback[seqNo] = callback;
	socket.send('{"seq":'+seqNo+',"domain":"Runtime","command":"evaluate","arguments":{"expression":"'+
	scriptString.replace(/[\"]/g,'\\"')
	+'","objectGroup":"console","includeCommandLineAPI":false}}');
	seqNo++;
	}

	remoteOnChange = function(result) { remoteURL = result.url; };


	function init() {

	var host = "ws://localhost:9222/devtools/page/5"; // Set page number!
	socket = new WebSocket(host);
	socket.onopen = function(msg){ run(); };
	socket.onmessage = function(msg){
	console.log('onMessage: '+msg.data);

	try
	{
	var responseObj = JSON.parse(msg.data);
	if (responseObj.seq > 0) {
	if (seqCallback[responseObj.seq] != undefined)
	{
	seqCallback[responseObj.seq](responseObj.body.result.description);
	}
	}
	if (responseObj.event == "inspectedURLChanged" && remoteOnChange != undefined)
	{
	remoteOnChange(responseObj.body);
	}

	if (responseObj.event == "loadEventFired" && remoteOnLoad != undefined)
	{
	remoteOnLoad();
	}
	} catch(err) {}
	}
	}

	function run(){
	remoteOnLoad = function(result) {

	// We might've ended up on the login page, so let's log in!
	if (remoteURL.indexOf("ServiceLogin") > 0 )
	remoteEval( " document.getElementById('Email').value = 'username'; "+
	" document.getElementById('Passwd').value = 'password'; "+
	" document.getElementsByTagName('form')[0].submit(); "
	, function(result) { alert(result); } );

	// We're home!
	if (remoteURL.indexOf("mail.google.com/mail/") > 0 )
	remoteEval( " try { document.getElementById('canvas_frame').contentWindow.document."+
	"getElementsByClassName( 'md' )[0].innerText } catch(e) { -1 }"
	, function(result) { // Waiting for AJAX:
	if (result == -1) { setTimeout(remoteOnLoad,2000); } // Try again in 2 sec.
	else { alert(result); } } ); // This should return scraped information
	// about your data usage on gmail! :D
	} ;

	// This happenes first:
	remoteEval(" location.href = 'http://gmail.com' "); //Let's go to Gmail!
	} ;


	</script>
	<body onload="init()">

	<textarea id="remoteText" cols="100" ></textarea><input type="button" value="Remote eval"
	onclick=" remoteEval( document.getElementById('remoteText').value , function(result) { alert(result); } ); " />

	</body>