betsbc.com results to xlsx converter

parser.rb

# encoding: UTF-8

require 'rubygems'
require 'net/http'
require 'uri'
require 'nokogiri'
require 'open-uri'
require 'axlsx'

$toto_base = "http://betsbc.com/toto/"

toto_list = $toto_base + "?action=old"
#toto_list = 'toto-list-example.htm'
toto_sample = 'toto-example.htm'

$user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.854.0 Safari/535.2"

$timeout = 25
$results = 0

def parse_links(result_link, wb, title)
        url = result_link.gsub(/^\/toto\//, $toto_base)
        result_doc = Nokogiri::HTML(open(url, 'User-Agent' => $user_agent), nil, 'utf-8')
        result_doc.encoding = 'utf-8'
        tables = result_doc.search('//table')

        sheet = wb.add_worksheet(:name => title)
        for table in tables;
            rows = table.search('tr')
            for row in rows;
                cells = row.search('td')
                plain_cells = []
                i = 0
                for cell in cells;
                    #puts "'"+cell.content+"'"
                    plain_cells.push(cell.text)
                    i = i + 1
                end
                sheet.add_row(plain_cells)
            end
        end

        return wb
end




puts "Loading page list..."
doc = Nokogiri::HTML(open(toto_list, 'User-Agent' => $user_agent), nil, 'utf-8')
doc.encoding = 'utf-8'

list_links = []
result_links = []
pages_links = []

pages_links = doc.search('//a[contains(@href, "?action=old")]')

lastlink = pages_links.last.attr('href')

lastpage = Integer(/p=(\d+)/.match(lastlink)[1])

if ARGV[0] then
  lastpage = Integer(ARGV[0])
end

puts "Last page: " + lastpage.to_s

i = 0

while i <= lastpage do

 if i > 0 then
    list_links.push(toto_list + "&p=" + i.to_s)
 else
    list_links.push(toto_list)
 end
 
 i += 1
end

p = Axlsx::Package.new
wb = p.workbook

count = 0

sleep($timeout)

for list_link in list_links;

  puts "Loading page " + list_link
  list_doc = Nokogiri::HTML(open(list_link, 'User-Agent' => $user_agent), nil, 'utf-8')
  list_doc.encoding = 'utf-8'
  res_links = list_doc.search('//a[contains(@href, "/toto/get.php")]')
  
  if $results > 0 and count > $results then
    break
  end

  for res_link in res_links;
    
    if $results > 0 and count > $results then
        break
    end
    
    url = res_link.attr('href').gsub(/^\/toto\//, $toto_base)
    
    title = res_link.text.gsub("Тотализатор ", "").gsub("Тираж ", "")
    puts "Loading results at " + url
    
    wb = parse_links(url, wb, title)  

    count = count + 1

    sleep($timeout)
    
  end

  sleep($timeout)
end



p.serialize('results-' + Time.now.to_i.to_s + '.xlsx')