is there any java script web crawler framework [closed]

There's a new framework that was just release for Node.js called spider. It uses jQuery under the hood to crawl/index a website's HTML pages. The API and configuration are really nice especially if you already know jQuery.

From the test suite, here's an example of crawling the New York Times website:

var spider = require('../main');

spider()
  .route('www.nytimes.com', '/pages/dining/index.html', function (window, $) {
    $('a').spider();
  })
  .route('travel.nytimes.com', '*', function (window, $) {
    $('a').spider();
    if (this.fromCache) return;

    var article = { title: $('nyt_headline').text(), articleBody: '', photos: [] }
    article.body = '' 
    $('div.articleBody').each(function () {
      article.body += this.outerHTML;
    })
    $('div#abColumn img').each(function () {
      var p = $(this).attr('src');
      if (p.indexOf('ADS') === -1) {
        article.photos.push(p);
      }
    })
    console.log(article);
  })
  .route('dinersjournal.blogs.nytimes.com', '*', function (window, $) {
    var article = {title: $('h1.entry-title').text()}
    console.log($('div.entry-content').html())
  })
  .get('http://www.nytimes.com/pages/dining/index.html')
  .log('info')
  ;

Try the PhantomJS. Not exactly a crawler, but could be easily used for that purpose. It has the fully-functional WebKit engine built-in, with an ability to save screenshots etc. Works as the simple command-line JS interpreter.

Server-side?

Try node-crawler: https://github.com/joshfire/node-crawler