gistfile1.rb

require 'rubygems'
require 'hpricot'
require 'open-uri'

class String
  def strip_tags
    self.gsub(/<[^<>]+>/,'')
  end
end

class WebPage
  attr_reader :content
  
  def initialize
    @content = yield
  end
  
  def self.from_file(path)
    new { File.open(path) { |f| f.read } }
  end

  def self.from_url(url)
    new { open(url) { |f| f.read } }
  end
  
  def select(selector, strip_tags = true)
    (page/selector).map { |i| strip_tags ? i.to_s.strip_tags : i.to_s }
  end
  
  def page
    @page ||= Hpricot(@content)
  end

end

# sample:
#
# p WebPage.from_url("http://www.google.com/analytics/features.html").select("h3")