twitimg.rb

# coding: utf-8

require 'mechanize'
require 'nokogiri'
require 'json'

m = Mechanize.new

m.user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36'

unless ARGV[0]
  puts "You need to give a twitter id."
  exit
end

id = ARGV[0]

`mkdir ./img_#{ id }`

# init_url = "https://twitter.com/#{ id }/media"
# m.get init_url

media_url = "https://twitter.com/i/profiles/show/#{ id }/media_timeline?include_available_features=1&include_entities=1&last_note_ts=0"


m.get media_url

json = JSON.parse m.page.body
max_id = 0

loop do
  html = Nokogiri::HTML json['items_html']
  html.css('span.media-thumbnail').map do |e|
    tweet_id = e['data-status-id']
    file_url = e['data-resolved-url-large']
    file_name = file_url.sub('https://pbs.twimg.com/media/','').sub(':large','')
    file_path = "./img_#{ id }/#{ tweet_id }_#{ file_name }"

    puts "tweet_id: #{tweet_id}"

    if File.exists? file_path
      puts "already exists : #{ file_path }"
    else
      puts "downloading : #{ file_path }"
      `wget #{ e['data-resolved-url-large'] } -o - -O #{ file_path }`
      puts "done"
      sleep 5
    end

    max_id = tweet_id
    puts ""
  end

  if json['has_more_items']
    sleep 2
    m.get "https://twitter.com/i/profiles/show/#{ id }/media_timeline?include_available_features=1&include_entities=1&last_note_ts=0&max_id=#{ max_id }&oldest_unread_id=0"
    json = JSON.parse m.page.body
  else
    break
  end
end