Triathlon scrapin'

scraper.rb

#!/usr/bin/ruby

require 'net/http'  

def get_url
  page = 'http://www.backprint.com/view_user_event.asp?PID=bp%18yG&EVENTID=81207&PWD=&BIB='
  bib_number = ARGV[0] 
  if bib_number.nil?
    puts "usage: scraper.rb bib_number"
    exit 1
  end
  total = page + bib_number
  total
end

url = get_url

html = Net::HTTP.get_response(URI.parse(url))

homepage = "homepage.html"
File.open(homepage, 'w') { |f| f.write(html.body) }

# commands
exec 'for i in `grep "thumbnail" homepage.html | sed "s/.*<img class=\"thumbnail\" src=\"\(.*\)\".*/\1/g" | grep brightroom | sed "s/t\.jpg/f\.jpg/g"` ; do wget $i ; done'

File.delete(homepage)