Node.js Web Crawler using Request and Cheerio

spider.js

var request = require('request');
var cheerio = require('cheerio');
var fs = require('fs');

var data = fs.createWriteStream('data.txt', {'flags': 'a'});

var urlsToCrawl = [];

var spider = function(url) {
	var index = urlsToCrawl.indexOf(url);
	// Remove the current url we're crawling from the list to be crawled.
	if(index > -1) {
		urlsToCrawl.splice(index, 1);
	}

	try {
		request(url, function(error, response, body) {
			if(!error && response.statusCode == 200) {
				var $ = cheerio.load(body);

				data.write($.html());
				console.log('Data saved for url: ' + url);

				$('a').each(function(i, element) {
					var link = element.attribs.href;
					urlsToCrawl.push(link);
				});
				// console.log(urlsToCrawl.length);
				return spider(urlsToCrawl[0]);
			} else {
				// This was probably a relative url or a page anchor,
				// which I don't account for yet.
				// console.log(urlsToCrawl.length);
				return spider(urlsToCrawl[0]);
				// console.log(error);
			}
		});
	} catch(error) {
		return spider(urlsToCrawl[0]);
		// console.log(error);
	}
};

spider('https://news.ycombinator.com/');

Crashes with this output from the console.

Data saved for url: http://www.avc.com/a_vc/2014/01/investing-in-startups-in-europe.html
(node) warning: possible EventEmitter memory leak detected. 11 listeners added. Use emitter.setMaxListeners() to increase limit.
Trace
    at Request.EventEmitter.addListener (events.js:160:15)
    at Request.init (c:\Users\Ace\Projects\crawler\node_modules\request\request.js:364:8)
    at Request.onResponse (c:\Users\Ace\Projects\crawler\node_modules\request\request.js:809:10)
    at ClientRequest.g (events.js:180:16)
    at ClientRequest.EventEmitter.emit (events.js:95:17)
    at HTTPParser.parserOnIncomingClient [as onIncoming] (http.js:1688:21)
    at HTTPParser.parserOnHeadersComplete [as onHeadersComplete] (http.js:121:23)
    at Socket.socketOnData [as ondata] (http.js:1583:20)
    at TCP.onread (net.js:525:27)
(node) warning: possible EventEmitter memory leak detected. 11 listeners added. Use emitter.setMaxListeners() to increase limit.
Trace
    at Request.EventEmitter.addListener (events.js:160:15)
    at Request.start (c:\Users\Ace\Projects\crawler\node_modules\request\request.js:610:8)
    at Request.end (c:\Users\Ace\Projects\crawler\node_modules\request\request.js:1226:28)
    at c:\Users\Ace\Projects\crawler\node_modules\request\request.js:412:12
    at process._tickCallback (node.js:415:13)
Data saved for url: http://www.asciiflow.com/
Data saved for url: https://lh5.googleusercontent.com/-dJsRfi7_Crw/Utl_miUi3II/AAAAAAAA8jM/2ODyIK015WI/s450-no/How+radians+work.gif
Data saved for url: http://www.slate.com/articles/technology/technology/2014/01/do_what_you_love_love_what_you_do_an_omnipresent_mantra_that_s_bad_for_work.html
Data saved for url: http://raganwald.com/2014/01/19/prototypes-are-not-classes.html
Data saved for url: http://en.wikipedia.org/wiki/Peelian_Principles
Data saved for url: https://bugzilla.redhat.com/show_bug.cgi?id=1054340
Data saved for url: http://paulgraham.com/cities.html
Data saved for url: http://scott.a16z.com/2014/01/17/success-at-work-failure-at-home/
Data saved for url: http://www.nbcnews.com/video/meet-the-press/54117741#54117741
Data saved for url: http://hoplon.io/
Data saved for url: http://homakov.blogspot.com/2014/01/cookie-bomb-or-lets-break-internet.html
Data saved for url: http://maxtaco.github.io/bitcoin/2014/01/16/how-jason-bourne-stores-his-bitcoin/

RangeError: Maximum call stack size exceeded

Hello. Your issue is that you do consequet calls (in your recursion) And you will always get this exception at some point, coz you never close scope.

Use event emitter instead of recursion

function spider(url){
.....
// finished parsing page
eventEmitter.emit('page.finished',result)
...
}
eventEmitter.on('page.finished',function(result){
//handle result
spider(nextUrl)
})
spider(firstUrl)