[Node.js] Intro to Web Scraping with Node and X-ray

Node and Xray have made web scraping a really simple affair. This video introduces you to the process of scraping all of the "a" tags off of a url and saving them to a .json file.

var Xray = require('x-ray');
var xray = new Xray();

//Grap <a> tag from google
xray('http://google.com', 'a', [
    {
        a: '',
        href: '@href',  // get href link
        css: '@class',   // get class
        id: '@id'
    }
]).write('results.json');

 

output:

[
  {
    "a": "Kuvahaku",
    "href": "http://www.google.fi/imghp?hl=fi&tab=wi",
    "css": "gb1"
  },
  {
    "a": "Maps",
    "href": "http://maps.google.fi/maps?hl=fi&tab=wl",
    "css": "gb1"
  },
  {
    "a": "Play",
    "href": "https://play.google.com/?hl=fi&tab=w8",
    "css": "gb1"
  },
  {
    "a": "YouTube",
    "href": "http://www.youtube.com/?gl=FI&tab=w1",
    "css": "gb1"
  },
  {
    "a": "Gmail",
    "href": "https://mail.google.com/mail/?tab=wm",
    "css": "gb1"
  },
  {
    "a": "Drive",
    "href": "https://drive.google.com/?tab=wo",
    "css": "gb1"
  },
  {
    "a": "Kalenteri",
    "href": "https://www.google.com/calendar?tab=wc",
    "css": "gb1"
  },
  {
    "a": "Lis�� »",
    "href": "http://www.google.fi/intl/fi/options/",
    "css": "gb1"
  },
  {
    "a": "Verkkohistoria",
    "href": "http://www.google.fi/history/optout?hl=fi",
    "css": "gb4"
  },
  {
    "a": "Asetukset",
    "href": "http://google.com/preferences?hl=fi",
    "css": "gb4"
  },
  {
    "a": "Kirjaudu sis��n",
    "href": "https://accounts.google.com/ServiceLogin?hl=fi&continue=http://www.google.fi/%3Fgfe_rd%3Dcr%26ei%3D51jMVcO8KK-r8weXlJawBw",
    "css": "gb4",
    "id": "gb_70"
  }
....
]