parser.rb

require_relative 'html_whitespace_cleaner'
require 'nokogiri'
require 'awesome_print'

class Parser
  attr_accessor :parsed_data

  def initialize
    @parsed_data = []
  end

  def open_file(location)
    html = File.read(location)
    clean_html = HTMLWhitespaceCleaner.clean(html)
    @nokogiri_document = Nokogiri.parse(clean_html)
    puts "FILE LOADED"
  end

  def post_args
    Hash[title:title, url: url, post_author: post_author, points: points, post_days_ago: post_days_ago]
  end

  def comment_args
    empty = []
    comment_authors.zip(comment_content,comment_days_ago).each do |item|
      empty << Hash[author: item[0], content: item[1], days_ago: item[2 ]]
    end
    empty
  end

private

  def title
    @nokogiri_document.css('title').inner_text.chomp(' | Hacker News')
  end

  def url
    @nokogiri_document.css('td.title').inner_text.scan(/\(([^\)]+)\)/)[0][0]
  end

  def post_author
    @nokogiri_document.css("span.score + a").text
  end

  def points
    @nokogiri_document.css("span.score").first.text
  end

  def post_days_ago
    @nokogiri_document.css("span.score + a + a").text.chomp(' days ago')
  end

  def comment_authors
    names = []
    @nokogiri_document.css(".comhead a:first-child").each do |name|
      names << name.inner_text
    end
    names
  end

  def comment_content
    container = []
    @nokogiri_document.css('.c00').each do |comment|
      # container << comment.inner_text.chomp('-----')
      container << "-> #{comment.inner_text[0,80]}..."
    end
    container
  end

  def comment_days_ago
    days = []
    @nokogiri_document.css(".comhead a:nth-child(2)").each do |data|
      days << data.text.chomp(" days ago")
    end
    days
  end

end