Crawling LinkedIn

linkedin.rb

require 'rubygems'
require 'mechanize'
require 'nokogiri'

@linkedin_username = "username"
@linkedin_password = "password"

agent = Mechanize.new
agent.user_agent_alias = "Mac Safari"
agent.follow_meta_refresh = true
agent.get("https://www.linkedin.com")

#Login to LI
form = agent.page.form_with(:action => '/uas/login-submit')
form['session_key'] = @linkedin_username
form['session_password'] = @linkedin_password
agent.submit(form)
pp "Login successful"

def search_class(page, search_query)
  output_array = Array.new
  page.search(search_query).each do |element|
    if !element.nil? && !element.inner_html.nil?
      output_array.push(element.inner_html)
    end
  end
  return output_array
end

def search_image_class(page, search_query)
  output_array = Array.new
  page.search(search_query).each do |element|
    if !element.nil? && !element["alt"].nil?
        p element["alt"]
      output_array.push(element["alt"])
    end
  end
  return output_array
end

names = []
titles = []
locations = []
industries = []
agent.get("http://www.linkedin.com/wvmx/profile?trk=nmp_profile_stats_viewed_by") do |page|
  names = search_image_class(page, 'img[@class="photo"]')
  titles = search_class(page, 'dd[@class = "title"]')
  locations = search_class(page, 'dd[@class="location"]')
  industries = search_class(page, 'dd[@class="industries"]')
end

names.each_with_index do |name, index|
  puts "#{name}\t#{titles[index]}\t#{locations[index]}\t#{industries[index]}"
end

Origin from: http://tomtunguz.com/crawling-the-most-under-rated-hack