gistfile1.txt

tweets = []
Dir['search*'].each do |f|
  File.open(f).readlines.join.scan(/(<li class="hentry status .*?<\/li>)/m).each do |tweet|        
    author = tweet[0].scan(/;">(.*?)<\/a>.*?<span id="msgtxt/m)[0].to_s
    text = tweet[0].scan(/<span id="msgtxt\d+" class="msgtxt \w+">(.*?)<\/span>/m)[0].to_s.gsub(/<.*?>/, '')    
    tweets << [author, text]
  end
end
puts tweets.uniq.sort.size