bskaggs/01_regex.rb

## 01_regex.rb
#!/usr/bin/env ruby
require 'rss'
require 'open-uri'

url = 'http://stackexchange.com/feeds/sites'

subdomains = []
domains = []
open(url) do |rss|
  feed = RSS::Parser.parse(rss, do_validate = false)
  feed.items.each do |item|
    uri = URI.parse(item.id.content)
    domain = uri.host
    if domain =~ /\.stackexchange\.com/
      subdomains << $`
    else
      domains << domain
    end
  end
end

def escape(domains)
  "(#{domains.sort.map{ |d| Regexp.escape(d) }.join('|')})"
end

puts "\\Ahttp://((#{escape(subdomains)}\.stackexchange\.com)|(#{escape(domains)}))\/tags\/"

## 02_output.txt
\Ahttp://(((academia|android|anime|apple|arduino|astronomy|aviation|beer|bicycles|biology|bitcoin|blender|boardgames|bricks|buddhism|chemistry|chess|chinese|christianity|codegolf|codereview|cogsci|cooking|craftcms|crypto|cs|cstheory|datascience|dba|diy|drupal|dsp|earthscience|ebooks|electronics|ell|english|expatriates|expressionengine|fitness|freelancing|french|gamedev|gaming|gardening|genealogy|german|gis|graphicdesign|ham|hermeneutics|hinduism|history|homebrew|islam|italian|japanese|joomla|judaism|linguistics|magento|martialarts|math|matheducators|mathematica|mechanics|meta|moderators|money|movies|music|networkengineering|opendata|outdoors|parenting|patents|pets|philosophy|photo|physics|pm|poker|politics|productivity|programmers|puzzling|quant|raspberrypi|reverseengineering|robotics|rpg|russian|salesforce|scicomp|scifi|security|sharepoint|skeptics|softwarerecs|sound|space|spanish|sports|sqa|startups|stats|sustainability|tex|tor|travel|tridion|unix|ux|video|webapps|webmasters|windowsphone|wordpress|workplace|writers).stackexchange.com)|((askubuntu\.com|mathoverflow\.net|pt\.stackoverflow\.com|serverfault\.com|stackapps\.com|stackoverflow\.com|superuser\.com)))/tags/
	#!/usr/bin/env ruby
	require 'rss'
	require 'open-uri'

	url = 'http://stackexchange.com/feeds/sites'

	subdomains = []
	domains = []
	open(url) do \|rss\|
	feed = RSS::Parser.parse(rss, do_validate = false)
	feed.items.each do \|item\|
	uri = URI.parse(item.id.content)
	domain = uri.host
	if domain =~ /\.stackexchange\.com/
	subdomains << $`
	else
	domains << domain
	end
	end
	end

	def escape(domains)
	"(#{domains.sort.map{ \|d\| Regexp.escape(d) }.join('\|')})"
	end

	puts "\\Ahttp://((#{escape(subdomains)}\.stackexchange\.com)\|(#{escape(domains)}))\/tags\/"