get the text of all the headlines on nytimes.com

nokogiri_example.rb

require 'rubygems'
require 'nokogiri'
require 'open-uri'

# fetch the html of the page
page = open("http://nytimes.com").read
# parse the page
doc = Nokogiri::HTML(page)

# use css selectors to get all the headlines on the page
# which, discovered by viewing source, are marked up as links inside of h2s, h3s, and h5s
headlines = doc.css("h2 a, h3 a, h5 a")

# print out the innter_html
for headline in headlines
  puts headline.inner_html
end