Removing infoboxes from Wikipedia pages with a regexp

info_boxes_wikpiedia_regexp.rb

# INFO extracted from : http://stackoverflow.com/questions/6331065/matching-balanced-parenthesis-in-ruby-using-recursive-regular-expressions-like-pe

require 'wikipedia'
wikipage = Wikipedia.find(title)

# This regular expression is not valid for infoboxes with '}' (i.e: http://en.wikipedia.org/wiki/The_Royal_Anthem_of_Jordan)
no_infoboxes = wikipage.content.gsub(/\{\{[^\}]*\}\}/, "")

# This regular expression makes use of recursive regular expressions so now handles recursive {{}} structures
no_infoboxes = wikipage.content.gsub(%r{(?<re>\{\{(?:(?> [^\{\}]+ )|\g<re>)*\}\})}x, "")