CareerjetSpider.rb

require 'rubygems'
require 'hpricot'
require 'open-uri'

class CareerjetSpider
  
  BASE = "http://www.careerjet.com/search/jobs"
  MONTH = { 'January' => 'Jan', 'February' => 'Feb', 'March' => 'Mar', 'April' => 'Apr', 'May' => 'May', 'June' => 'Jun', 'July' => 'Jul', 'August' => 'Aug', 'September' => 'Sep', 'October' => 'Oct', 'November' => 'Nov', 'December' => 'Dec'}
  
  attr_reader :page
  
  def initialize(where = nil, what = nil, page = 1)
    puts @url = get_url(where, what)
    @page = page
  end
  
  def next_page()
    @page += 1
  end
  
  def get_url(where = nil, what = nil)
    URI.escape("#{BASE}?s=#{what}&l=#{where}&p=#{@page}")  
  end
  
  def items
    items = []
    doc = open(@url) { |f| Hpricot(f) }
    pp (doc/'html/body/table/tbody/tr/td/div[6]/div/div/div[3]/p[3]/span')
     doc.search("//div[@class='job']").each do |job|  
       items << get_elements(job)
     end  
     
    items
  end
  
  
  def get_elements(job)
    hash = {
      :location => (job/"//span[@class='locations_compact']").inner_text.gsub('-', '').strip,   
      :title => (job/"//a[@class='title_compact']").inner_text.strip,
      :hash => (job/"//a[@class='title_compact']").first.attributes['href'].gsub('/job/', '').gsub('.html','').strip,
      :company => (job/"//span[@class='company_compact']").inner_text.strip,
      :url_company =>  get_url_company((job/"//span[@class='site']").inner_html.match("(').*(')").to_s.gsub("'", '')),
      :date => get_date((job/"//span[@class='date_compact']").inner_text.gsub('-', '').strip),
      :description => (job/"//p[@class='advertise_compact']").inner_text.strip
   }
  end

  def get_url_company(str)
    res = ''
    str.length.times do |i|
      res += (str[i]-2).chr
    end
    res
  end
  
  def get_date(date)
    split =  date.split(' ')
    month = split.first
    day = split.last
    Time.utc(Time.now.year, MONTH[month], day)
  end
end