Created
September 27, 2008 11:40
-
-
Save beastaugh/13315 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env ruby | |
require 'rubygems' | |
require 'hpricot' | |
require 'open-uri' | |
# Screen scraper for xkcd. The basic idea is to find out whether the comic | |
# always has the longest title of any image on the page. Inspired by this | |
# Hacker News posting: http://news.ycombinator.com/item?id=316621 | |
comic_url = 'http://imgs.xkcd.com/comics/' | |
counter = [] | |
(1..481).each do |i| | |
begin | |
doc = open("http://xkcd.com/#{i}/") { |f| Hpricot(f) } | |
images = doc.search("img").select {|e| e.has_attribute?("title")}.sort_by { |img| | |
img.get_attribute("title").length | |
}.reverse | |
if images.first.get_attribute('src')[0, comic_url.length] != comic_url | |
counter.push(i) | |
end | |
puts "Processed comic #{i}..." | |
rescue | |
puts "Something went wrong while trying to process comic #{i}" | |
end | |
end | |
if counter.length > 0 | |
comic_nums = counter.inject {|join, n| "#{join}, #{n}" } | |
puts "The following comics don't have the longest title: #{comic_nums}." | |
else | |
puts "The comic is alway the image with the longest title on xkcd." | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment