Shitty code to sort tweets by reply ratio

sort_tweets_by_reply_ratio.rb

require 'twitter'
client = Twitter::REST::Client.new do |config|
  config.consumer_key        = "your_consumer_key"
  config.consumer_secret     = "your_consumer_secret"
  config.access_token        = "your_access_token"
  config.access_token_secret = "your_access_token_secret"
end

def collect_with_max_id(collection = [], max_id = nil, &block)
  response = yield(max_id)
  collection += response
  response.empty? ? collection.flatten : collect_with_max_id(collection, response.last.id - 1, &block)
end

def client.get_all_tweets(user)
  collect_with_max_id do |max_id|
    options = {count: 200, include_rts: false}
    options[:max_id] = max_id unless max_id.nil?
    user_timeline(user, options)
  end
end

def get_reply_count(tweet)
  doc = HTTParty.get(tweet.url.to_s)
  page_parser = Nokogiri::HTML(doc)
  reply_count_text = page_parser.css('span.ProfileTweet-actionCount')
                                .first
                                .attributes['data-tweet-stat-count']
                                .value
  reply_count_text.to_i
rescue StandardError => e
  puts "Something went wrong, probably no replies #{e}"

  0
end

def client.ratio_report_for_user(handle)
  puts "Retrieving as many tweets as Twitter's API will allow. . ."
  all = get_all_tweets(handle).reject do |tweet|
    # Some tweets go missing, which breaks :reply?
    # This is unfortunate, because tweets starting with @ aren't always replies.
    # But this will have to do.
    replyish = tweet.text.start_with?('@')
    tweet.reply? || replyish
  end
  puts "Retrieved #{all.count} tweets. . .}"

  require 'nokogiri'
  require 'HTTParty'

  tweets_by_id = {}
  all.each do |tweet|
    tweets_by_id[tweet.id] = tweet
  end

  puts 'Scraping reply counts from the interwebs (this takes a wee while). . .'
  reply_counts = {}

  thread_count = all.count / 20
  chunks = all.each_slice(thread_count).to_a
  chunks.map do |chunk|
    Thread.new do
      chunk.each { |tweet| reply_counts[tweet.id] = get_reply_count(tweet) }
    end
  end.each(&:join)
  puts 'Done, now crunching some numbers...'

  ratio_by_tweet_id = {}
  all.each do |tweet|
    reply_count = reply_counts[tweet.id] || 0
    popularity = (tweet.retweet_count + tweet.favorite_count)
    popularity = 1 if popularity.zero?
    ratio = reply_count / popularity.to_f
    ratio_by_tweet_id[tweet.id] = ratio
  end

  sorted = all.sort_by { |tweet| -ratio_by_tweet_id[tweet.id] }

  sorted.map do |tweet|
    reply_count = reply_counts[tweet.id]
    ratio = ratio_by_tweet_id[tweet.id]
    "#{tweet.url}\nRatio: #{ratio}, Replies: #{reply_count}, RTs: #{tweet.retweet_count}, Favs: #{tweet.favorite_count}\n#{tweet.text}\n"
  end.join("\n")
end

def save_report_for(client, handle)
  puts "Beginning report for #{handle}"
  report = client.ratio_report_for_user(handle)
  File.open("#{handle}.txt", 'w') { |file| file.write(report) }
  puts "Saved #{handle}.txt, all done!"
end