Lists names, urls, and text of all of a HubPages users' hubs

hub_lister

#http://www.codegurl.com/2012/02/disguising-load-times-w-information.html
require 'nokogiri'
require 'open-uri'

def create_base_url(username)
  #takes hub username and turns it into url using 'lastest'
  base_url = "http://#{username}.hubpages.com/hubs/latest".to_s
end

def get_index_pages(base_url, username)
  index_pages = []
  doc = Nokogiri::HTML(open(base_url))
  range = doc.xpath('//span[@class="range"]').inner_text
  #finds number of hubs in 'range' string
  str_array = range.split(' ')
  number_of_hubs = str_array[2]
  #strips out unnessesary info from range string and returns number of hubs
  number_of_hubs = number_of_hubs.to_i
  number_of_index_pages = number_of_hubs / 10 + 1
  #finds the number of index pages, 10 hubs per page, one extra page for remainder.

  while number_of_index_pages != 0
    number_of_index_pages = number_of_index_pages.to_s
    index_pages << "http://#{username}.hubpages.com/hubs/latest?page=#{number_of_index_pages}"
    number_of_index_pages = number_of_index_pages.to_i
    number_of_index_pages = number_of_index_pages - 1
  end
  return index_pages
end

def get_hub_urls(index_list)
  hubs = []
    index_list.each do |something|
      doc = Nokogiri::HTML(open(something))
      doc.xpath('//div[@class="hub_pic"]/a').each do |e|
        hubs << e['href']
      end
    end
  return hubs
end

def pull_text(hub_urls)
  hubs = Hash.new
  results = []
  hub_urls.each do |something|
    doc = Nokogiri::HTML(open(something))
    main_text = doc.xpath('//div[@class="module moduleText color0"]').inner_text
    blue_text =  doc.xpath('//div[@class="module moduleText color2"]').inner_text
    grey_text =  doc.xpath('//div[@class="module moduleText color1"]').inner_text
    table_text = doc.xpath('//div[@class="module moduleTable color0"]').inner_text
    title = doc.search('title').inner_text
    all_text = main_text + blue_text + grey_text + table_text
    hubs[title] = all_text
 end
   return hubs
end

def clean_text(hubtxt_hash)
  hubtxt_hash.each |key|
  key = key.delete(",").gsub(" ", ",")
  key = key.delete("\n").split(",")
  return hubtxt_hash
end

puts "Enter HubPages username:"
username = gets.chomp
base_url = create_base_url(username)
index_pages = get_index_pages(base_url, username)
hub_urls = get_hub_urls(index_pages)
text = pull_text(hub_urls)