Ruby script to archive a copy of your Instagram images and movies using the official basic display api

instagram.rb

# Ruby script to archive a copy of your Instagram images and movies
# USAGE: ruby ig.rb

# https://developers.facebook.com/docs/instagram-basic-display-api/

# Setup Instagram App
  # 1. login to your facebook developer account
  # 2. create an app
  # 3. setup instagram basic display api
  # 4. invite yourself as an instagram tester

# Accept Instagram Tester invite
  # 1. login to your instagram account
  # 2. settings --> apps and websites --> tester invites --> accept invitation

# Generate and Retrieve Access Token
  # 1. login to facebook developer account
  # 2. goto your app
  # 3. basic display --> user token generator --> generate token
  # 4. save token as an environment variable

access_token = ENV['JEKYLL_INSTAGRAM_ACCESS_TOKEN']

require 'date'
require 'json'
require 'httparty'

def archive_media(id, url, type)
  puts url
  # Video or Image
  if type == 'VIDEO'
    file_extension = '.mp4'
  else
    file_extension = '.jpg'
  end
  # Archive Image
  filename = 'instagram/'+id+file_extension
  if !File.exist? filename
    File.open(filename, "w") do |file|
      file.binmode
      HTTParty.get(url, stream_body: true) do |fragment|
        file.write(fragment)
      end
    end
  end
  return filename
end

# Media Request
media_request = HTTParty.get('https://graph.instagram.com/me/media?fields=id,permalink,caption,media_type,media_url,timestamp,children&access_token='+access_token)
media = JSON.parse(media_request.to_s)

# Process Data
if media and media.has_key? 'data'
  media['data'].each do |asset|
    asset_date = Date.parse(asset['timestamp'])
    # Archive media
    archive_media(asset['id'], asset['media_url'], media['media_type'])
    # Children?
    if asset['children'] and asset['children']['data'].length > 0
      asset['children']['data'].each_with_index do |child_asset,idx|
        # skip the first asset
        next if idx == 0 
        # look up media asset
        media_request = HTTParty.get('https://graph.instagram.com/'+child_asset['id'].to_s+'?fields=id,media_type,media_url,timestamp&access_token='+access_token)
        if media_request
          media = JSON.parse(media_request.to_s)
          # Archive media
          archive_media(media['id'], media['media_url'], media['media_type'])
        end
      end
    end # children?
  end # data
end # media?