Flickr Downloader

download

#!/usr/bin/env ruby

require 'fileutils'
require 'flickraw'
require 'open-uri'
require 'set'
require 'zaru'

def download_page(destination_dir:, page:)
  count = 0
  flickr.photos.search(page:page, per_page:300, sort:'date-posted-asc', user_id:'me').each do |p|
    succeeded = false
    while !succeeded
      begin
        download_photo destination_dir:destination_dir, p:p
        succeeded = true
      rescue Net::OpenTimeout, JSON::ParserError, Net::ReadTimeout
        puts 'Error getting the next list of photos to download... waiting to try again...'
        sleep 20
      end
    end
    count += 1
  end
  count
end

def download_photo(p:, destination_dir:)
  existing_file = downloaded(directory:destination_dir, id:p.id)
  if existing_file && !downsized?(existing_file)
    puts "#{p.id} exists. skipping."
    return
  end
  info = flickr.photos.getInfo(photo_id:p.id)
  url = FlickRaw.url_o(info)
  basic_name = "#{p.id};#{info.dates.taken.gsub(':', '-')},#{info.title}"
  extension = url[url.rindex('.')+1..-1]
  name = Zaru.sanitize! basic_name, padding:4
  destination = "#{destination_dir}/#{name}.#{extension}"
  puts name
  if File.exist?(destination)
    puts '   - exists. skipping.'
    return
  end
  original = true
  succeeded = false
  sizes = ['_n', '', '_z', '_b'] # n=320, ''=500, z=640, b=1024
  while !succeeded
    begin
      IO.copy_stream(open(url), destination)
      if FileUtils.identical?(destination, 'missing-file.jpg')
        File.delete(destination)
        destination = "#{destination_dir}/#{name} (NOT ORIGINAL).#{extension}"
        puts "   - missing. downloading smaller size to #{destination}."
        url = FlickRaw.send("url#{sizes.pop}", info)
        original = false
      else
        File.delete(existing_file) if existing_file && (original == true)
        succeeded = true
      end
    rescue Net::OpenTimeout, Net::ReadTimeout
      puts '   - error downloading... waiting to try again...'
      sleep 20
    end
  end
end

def downloaded(directory:, id:)
  Dir["#{directory}/*"].each do |f|
    return f if File.basename(f).start_with?("#{id};")
  end
  return nil
end

def downsized?(f)
  File.basename(f).include?('(NOT ORIGINAL)')
end

FlickRaw.api_key = '...your API key...'
FlickRaw.shared_secret = '...your shared secret...'

token = flickr.get_request_token
auth_url = flickr.get_authorize_url(token['oauth_token'], :perms => 'delete')

puts "Open to complete authication: #{auth_url}"
puts 'Paste the generated token here.'
verify = gets.strip

begin
  flickr.get_access_token(token['oauth_token'], token['oauth_token_secret'], verify)
  login = flickr.test.login
  username = login.username

  # flickr.access_token = '...your access token if you don't want to reauthenticate...'
  # flickr.access_secret = '...your secret if you don't want to reauthenticate...'
  # username = '...your username so that it can be printed below...'

  puts "You are now authenticated as #{username} with token #{flickr.access_token} and secret #{flickr.access_secret}"
  destination_dir = 'downloaded'
  destination_dir = 'download'
  FileUtils.mkdir_p destination_dir
  # existing = Set.new(
  #   Dir["#{destination_dir}/*"].map do |f|
  #     /^\d+/.match(File.basename(f))[0].to_i
  #   end
  # )
  page = 1
  loop do
    count = 0
    succeeded = false
    while !succeeded
      begin
        count = download_page destination_dir:destination_dir, page:page
        succeeded = true
      rescue Net::OpenTimeout, JSON::ParserError, Net::ReadTimeout
        puts 'Timed out... waiting...'
        sleep 20
      end
    end
    page += 1
    break if count == 0
  end
rescue FlickRaw::FailedResponse => e
  puts "Authentication failed : #{e.msg}"
end