JSON Parser to CSV for Instagram scraper

ig_json_parser.rb

require 'json'
require 'csv'

puts "=======  JSON Parser for Instagram  ========="
puts "==================  v1.0  ==================="
puts "==============  Megumi Aliya  ==============="

def parse_posts(account_name)
  pages = Dir.glob("#{account_name.chomp}/#{account_name.chomp}_posts_page_*.json")
  total_pages = pages.sort_by { |s| s.scan(/\d+/).first.to_i }.last.split("_").last.delete(".json").to_i
  posts_pages = []
  puts "Account : #{account_name.chomp} with #{total_pages} pages will be parsed and exported to CSV file"

  pages.each do |file|
    file = File.read(file)
    res = JSON.parse(file)
    posts_pages << res["data"]["user"]["edge_owner_to_timeline_media"]["edges"]
  end

  CSV.open("#{account_name.chomp}_posts.csv", "w", 
    :write_headers=> true,
    :col_sep => ";",
    :headers => ['id', 'display_url', 'post_caption', 'total_comment', 'total_like', 'taken_at_timestamp']
  ) do |csv|
    posts_pages.each do |posts|
      posts.each do |post|
        # byebug
        post_id = post["node"]["id"]
        post_caption = (post["node"]["edge_media_to_caption"]["edges"][0]["node"]["text"] rescue '')
        total_comment = post["node"]["edge_media_to_comment"]["count"]
        total_like = post["node"]["edge_media_preview_like"]["count"]
        taken_at_timestamp = post["node"]["taken_at_timestamp"]
        display_url = post["node"]["display_url"]

        csv << [post_id, display_url, post_caption, total_comment, total_like, taken_at_timestamp]
      end
    end
  end
end

def parse_profile(account_name)
  puts "Account : #{account_name.chomp} profile will be parsed and exported to CSV file"

  file = File.read("#{account_name.chomp}/#{account_name.chomp}_profile.json")
  res = JSON.parse(file)
  profile = res["graphql"]["user"]

  CSV.open("#{account_name.chomp}_profile.csv", "w", 
  :write_headers=> true,
  :col_sep => ";",
  :headers => ['id', 'username', 'biography', 'external_url', 'followed_by', 'follow', 'fullname', 'is_bussiness_account', 'is_joined_recently', 'is_private', 'is_verified', 'profile_pic_url']) do |csv|
    id = profile['id']
    username = profile['username']
    biography = profile['biography']
    external_url = profile['external_url']
    followed_by = profile['edge_followed_by']['count']
    follow = profile['edge_follow']['count']
    fullname = profile['full_name']
    is_bussiness_account = profile['is_business_account']
    is_joined_recently = profile['is_joined_recently']
    is_private = profile['is_private']
    is_verified = profile['is_verified']
    profile_pic_url = profile['profile_pic_url_hd']

    csv << [id, username, biography, external_url, followed_by, follow, fullname, is_bussiness_account, is_joined_recently, is_private, is_verified, profile_pic_url]
  end
end

print "Input account name : "
input = gets

if input.chomp == '*'
  Dir.glob("*/").each do |account_name|
    parse_posts(account_name.delete("/"))
    parse_profile(account_name.delete("/"))
  end
else
  parse_posts(input.chomp)
  parse_profile(input.chomp)
end

puts "Parsing posts JSON has been finished."