wikipedia_analytics_minimum.rb

## Analyze Wikipedia access data
# Data format
# https://wikitech.wikimedia.org/wiki/Analytics/Data/Pageviews
# Files
# https://dumps.wikimedia.org/other/pageviews/

filename = "pageviews-20170101-000000"
file = File.open(filename)
access_data = []
file.each_line do |text|
  data = text.split
  if data[0] == "ja" && data[1] =~ /駅\z/
    access_data.push({title: data[1], count: data[2]})
  end
end
file.close

# count順にソート
result = access_data.sort_by do |i|
  i[:count].to_i
end

# トップ10表示
result.reverse.first(10).each do |i|
  puts i
end