Analyze tags in blogs from Jekyll-style front-matters

parse_front_matter_data.rb

require 'front_matter_parser'
require 'csv'

# Usage: ParseFrontMatterData.new.save_csv
# Will create `data.csv` in the current working directory
class ParseFrontMatterData
  attr_accessor :blog_files, :front_matters

  def initialize
    @blog_files = get_blog_files
    @front_matters = parse
  end

  def get_blog_files
    Dir.glob('source/blog/**/*.html.markdown.erb')
  end

  def keys_to_select
    %w[date title headline author tags]
  end

  def parse
    @blog_files.map do |post|
      md = File.read post
      parsed = FrontMatterParser::Parser.new(:md).call(md)
      parsed.front_matter.select { |k, _| keys_to_select.include? k }
    end
  end

  def save_csv
    CSV.open('data.csv', 'wb') do |csv|
      csv << @front_matters.first.keys
      @front_matters.map do |h|
        csv << h.values
      end
    end
  end
end

ParseFrontMatterData.new.save_csv