first to create web crawler with node js

webcrawler.js

var http = require('http'),
    cheerio = require('cheerio');


startUrl = 'http://www.renren.com';

var urls = [startUrl];
var tags = ["div","h1","h2","h3","h4","h5","img","a"]

// Utility function that downloads a URL and invokes callback
function download(url, callback){
  http.get(url, function(res){
    var data="";

    res.on('data', function(chunk){
      data += chunk;
    });

    res.on('end', function(){
      callback(data);
    });

  }).on('error', function(){
    callback(null);
  });

}


function seriesDownloader(urls,counter, callback){

  var urlPattern = /^(https?:\/\/)([\da-z\.-]+).\.([a-z\.]{2,10})([\/\w\.-]*)*\/?$/;

  download(urls[counter],function(data){
    if(data){

      console.log("---------"+urls[counter]+"----------");

      var $ = cheerio.load(data);
      callback($)

      // grape next url
      counter++;
      if(!!urls[counter]){
        seriesDownloader(urls,counter);
      }else{
        console.log("-----end of crawler------");
        return;
      }

    }else{
      console.log("error");
    }
  });
}

function analy($){
  var result = {}

  tags.forEach(function(e){
    result[e] = $(e).length
  })
  console.log(result)
}

seriesDownloader(urls, 0, analy);