gistfile1.rb

# encoding: utf-8
require 'open-uri'
url = "http://ru.wikipedia.org/w/index.php?title=%D0%A1%D0%BF%D0%B8%D1%81%D0%BE%D0%BA_%D0%BC%D0%B5%D1%82%D1%80%D0%BE%D0%BF%D0%BE%D0%BB%D0%B8%D1%82%D0%B5%D0%BD%D0%BE%D0%B2&action=raw"
wiki = open(url).read

result = wiki.lines.map { |line|
  next unless line.start_with?('*')

  #* [[Лондон]] ([[1863]]) — [[Лондонский метрополитен]] — 11 линий, 408 км, 260 станций
  
  parts = line.sub("''", '').sub("): ", ") —").sub("]]: ", "]] —").split('—')

  data = {}
  if parts[0] =~ /\[\[(.*)\]\].*\((.*)\)/
    data.update(city: $1, year: $2)
  else
    parts[0] =~ /\[\[(.*)\]\]/
    data[:city] = $1
  end
  data[:name] = parts[1]
  metrics = parts[2]
  
  if data[:year] =~ /(\d{4})/
    data[:year] = $1.to_i
  end
  
  if metrics =~ /([^\s]+)\s*км/
    data[:length] = $1.index(',') ? $1.sub(',', '.').to_f : $1.to_i
  end

  if metrics =~ /(\d+) лин/
    data[:lines] = $1.to_i
  end

  if metrics =~ /(\d+) стан/
    data[:stations] = $1.to_i
  end

  #data[:name] = data[:name].split(']]', 2)[0]

  data[:length].nil? ? nil : data
}.compact


puts result.sort_by { |row| row[:km] }.reverse.map { |data|

  "| [[#{data[:city]}]] || #{data[:name]} || #{data[:year]} || #{data[:lines]} || #{data[:stations]} || #{data[:length]}"

}.join("\n|-\n")