Got a huge dir of movies, wants to know what movie to see according to IMDB ratings.

imdb_get_dir.rb

require 'uri'

def safe_comparison(matrix)
  matrix.map do |row|
    row.map do |el|
      el = el.to_s
    end
  end
end

results = Dir.glob('*/').map do |dir|

  # build search query
  movie_name = dir.gsub("/", "")
  url = "http://www.imdb.com/find?ref_=nv_sr_fn&q=#{URI.escape(movie_name)}&s=all"
  url = url.gsub("'","").gsub('"',"") # hack so cli doesn't barf, imdb doesn't care.

  # get the imdb link for this movie
  imdb_title_link = %x{xidel '#{url}' --extract "//css('a')/@href" | grep 'title/' | head -1| awk '{print "http://imdb.com/"$1}' }
  imdb_title_link.chomp!

  # rating, genre for this movie
  info = %x{xidel '#{imdb_title_link}' --extract "//css('div.star-box-giga-star')"  --extract '//css(".infobar")/a' }.split.map(&:chomp)
  rating = info.shift
  genres = info.join(",")

  [ rating, genres, movie_name, imdb_title_link.chomp ]
end

# save
File.open("/tmp/imdb_results.out", "w") do |f|
  f.puts(results.inspect)
end

puts "========================"
puts "ORDERED MOVIE BY RATING"
puts "========================"
puts

safe_comparison(results).sort.reverse.map do |rating, genres, movie_name, link|
    printf "%-3s %-30s %-36s %s\n", rating.chomp, genres, movie_name, link
end; 'ok'

File.open("/tmp/imdb_results.out", "w") do |f|
  f.puts(results.inspect)
end

Example output:

https://gist.githubusercontent.com/shaiguitar/4891a11d51bb54cf9a3e/raw/a608fa264fbf9420a9eb0a04e0bfdeb9171eb6c8/gistfile1.txt

Alternative data: http://www.imdb.com/interfaces

Cassandra's: https://gist.githubusercontent.com/shaiguitar/c93ccc6528fbaeaa6e7e/raw/c8f76de9f694199127506ea9142b44cf32e39a69/gistfile1.txt