Simple script for testing http://xkcd.com/903/ alltext trivia

wiki.rb

# encoding: UTF-8

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

target = 'Philosophy'
links = {}


def get_first_article(article)
  base = 'http://en.wikipedia.org/wiki/'
  doc = Nokogiri::HTML(open(base+article, 'User-Agent' => 'ruby'))
  doc.css('#bodyContent > p').each do |p|
    link = Nokogiri::HTML(formatParagraph(p.to_s)).css('a').find{ |l| l['href'].match(/^\//) }
    return link['href'].gsub(/^\/wiki\//, '') if link
  end
end

def formatParagraph(text)
  # remove parenthesis
  r = /\(.[^\(]*?\)/
  mark = '@#$'
  while text.match r
    text.gsub!(r) {|m| m.to_s.gsub(/<|>/, '').gsub('(', mark).gsub(')', mark.reverse)}
  end
  text.gsub(mark, '(').gsub(mark.reverse, ')')
end

def map_links(start, target, links)
  puts "\nStarting new mapping"
  current = start
  while(current && current != target && !links[current])
    puts current
    last = current
    current = links[current] = get_first_article(current).to_s
  end

  links
end

pages = [
  'Kudremukh_Iron_Ore_Company_Ltd.',
  'Pivotal_Rockordings',
  'Pyawbwe',
  'McMurtrey_Aquatic_Center',
  'Melandryidae',
  'Jafet_Soto',
  'Judy_Smith_Torrie',
  'A_Different_Kind_of_Love_Song',
#  'New_Frontier',
  '2003_League_of_Ireland',
  'The_Grid_(TV_miniseries)',
  'List_of_divided_U.S._Routes',
  'Lilydale,_Victoria',
  'Endo_(band)',
  'Makoto_Kosaka'
]

pages.each do |page|
  links = map_links(page, target, links)
end

g = GraphViz::new( "structs", "type" => "graph" )
g[:rankdir] = "LR"
g.node[:color]    = "#ddaa66"
g.node[:style]    = "filled"
g.node[:shape]    = "box"
g.node[:penwidth] = "1"
g.node[:fontname] = "Trebuchet MS"
g.node[:fontsize] = "8"
g.node[:fillcolor]= "#ffeecc"
g.node[:fontcolor]= "#775500"
g.node[:margin]   = "0.0"

# set global edge options
g.edge[:color]    = "#999999"
g.edge[:weight]   = "1"
g.edge[:fontsize] = "6"
g.edge[:fontcolor]= "#444444"
g.edge[:fontname] = "Verdana"
g.edge[:dir]      = "forward"
g.edge[:arrowsize]= "0.5"

pages = (links.keys + links.values).uniq.compact

pages.each do |page|
  g.add_node(page).label = page
end

links.each do |source, link|
  g.add_edge(source, link) if source && link
end

g.output( :path => '/opt/local/bin', :pdf => "philosophy.pdf" )

#if !current
#  puts "We reached a dead end on #{last}"
#elsif current == target
#  puts "We arrived from start #{start} to #{target} in #{links.size} steps"
#else
#  puts "We entered a loop starting on #{current}"
#end

That looks really nice!