grabs uk fund prices

uk_fund.rb

require 'rubygems'
require 'hpricot'
require 'open-uri'
require 'activesupport'
require 'morph'

Hpricot.buffer_size = 2621444

@@step_off = 1
def open_doc url
  begin
    open(url, {
      "User-Agent" =>
          "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
      "Accept" =>
          "text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5",
      "Accept-Language" =>
          "en-us,en;q=0.7,en-gb;q=0.3",
      "Accept-Charset" =>
          "ISO-8859-1,utf-8;q=0.7,*;q=0.7"
    }) { |f| Hpricot(f) }
  rescue Exception => e
    @@step_off += 1
    sleep 2 * @@step_off
    open_doc url
  end
end

# example usage:
# id = 'rufferllp/ruffer/RZBST'
# fund = Fund.new id
# fund.to_csv
class Fund
  include Morph

  def initialize fund=nil
    if fund
      url = "http://funds.ft.com/funds/#{fund}"
      doc = open_doc url

      each_entry doc do |label, value|
        morph(label, value)
      end

      time = Time.now.utc.to_s
      self.time = time.match(/\d\d:\d\d:\d\d/)[0]
      self.name = doc.at('.FundNameHeader').inner_text
      self.url = url
      self.date = Date.today.to_s
      self.id_name = "#{url}##{date}"
    end
  end

  def bid_price
    @bid_offer ? bid_gbx : nav_gbx
  end

  def offer_price
    if respond_to? :offer_gbx
      @bid_offer ? offer_gbx : ''
    else
      @bid_offer ? offer_ : ''
    end
  end

  def to_csv
    "#{name}, GBP, #{bid_price}, #{offer_price}, #{percentage_change}"
  end

  private

  def each_entry doc
    get_price_rows(doc).each do |row|
      cells = (row/'td').collect(&:inner_text).collect(&:strip).delete_if(&:blank?)
      cells.in_groups_of(2) do |entry|
        yield entry[0].gsub('-','_'), entry[1]
      end
    end
  end

  def get_price_rows doc
    rows = rows_starting 'Bid(GBX)', doc
    @bid_offer = rows.size > 0
    rows = rows_starting 'Nav(GBX)', doc unless @bid_offer
    rows
  end

  def rows_starting label, doc
    rows = (doc/"table/tr/td/span/[text()='#{label}']/../../../../tr")
    if rows.size == 0
      rows = (doc/"table/tr/td[text()='#{label}']/../../tr")
    end
    rows
  end

end