Regex for URLs

url_reg.rb

#/^(\w+\:\/\/)?([\w+|\-\.\w+?\b]*)(:\d{1,5})?(\S*)?/

#When used with the .match method in Ruby on a URL string, this regex produces a Match object 
#with the following array of matches: [whole url, protocol, domain, port, relative path]

#Examples (try these out in IRB or Pry):

url_reg = /^(\w+\:\/\/)?([\w+|\-\.\w+?\b]*)(:\d{4})?(\S*)?/

"http://www.google.com/index.html".match(url_reg).to_a.each_with_index do |el, index|
  puts "#[#{index}] #{el}"
end

#[{0}] http://www.google.com/index.html
#[{1}] http://
#[{2}] www.google.com
#[{3}] 
#[{4}] /index.html

"https://sx3jvhfgzhw44p3x.onion/".match(url_reg).to_a.each_with_index do |el, index|
  puts "#[{index}] #{el}"
end

#[{0}] https://sx3jvhfgzhw44p3x.onion/
#[{1}] https://
#[{2}] sx3jvhfgzhw44p3x.onion
#[{3}] 
#[{4}] /

#After splitting in this manner, each part can be further parsed to get subdomains, top level domains,
#individual directories, etc.