royw-imdb 0.0.17 → 0.0.19

data/History.txt

@@ -0,0 +1,90 @@
+0.0.7 royw-imdb
+    added Also Known As (aka) title matching
+    added ImdbSearch.find_id
+    added ImdbMovie.release_year
+    added ImdbMovie.raw_title
+    added ImdbMovie.video_game?
+    added ImdbMovie.also_known_as
+    added ImdbMovie.mpaa
+    added ImdbMovie.certifications
+
+    cleaned up merges, spec now passes
+    Merge branch 'master' of git://github.com/caleb/imdb
+    merged jasonrudolph branch
+    merged kieranj branch
+    forked from porras-imdb
+
+0.0.6
+    Merge patch from different fork
+    Correctly parse movies with only one writer
+    Add CHANGELOG and bump version to v0.0.6
+    Add support for searches that result in an exact match
+    Add method to retrieve movie year ...
+      - We could already retrieve the release date, but not all movies
+        have a release date (e.g., http://www.imdb.com/title/tt0464826/).
+      - All movies seem to have a year.
+    Strip duplicate movies from the search results
+    updated gemspec
+    changed poster url
+    Updated README
+    Added method to retrieve user rating
+    ImdbImage
+    now returns movie title instead of page title
+    now fetches large poster from different url
+    now works for multiple directors
+    Revert "Revert "Revert "Revert "default rake task""""
+
+    This reverts commit ed13a2fc544a0b9bbb2276a6ab38bc6a049c5972.
+    Revert "Revert "Revert "default rake task"""
+
+    This reverts commit b2114e2b342e11d3ad9bf8e857d2179d254ecf4c.
+    Revert "Revert "default rake task""
+
+    This reverts commit c662da7f4de5ad510ce706d38de1606f08b211d3.
+    Revert "default rake task"
+
+    This reverts commit 25dcceb4ba63f028b9683f7841b831b96db4d3f1.
+    default rake task
+    Dependencies on gemspec
+    Gitignoring *.gem
+    Uses IMDB to search because of partial matches (which Google doesn't find)
+    Doc updated + Gem version increment
+    Testing encoding issues
+    ImdbMovie#aspect_ratio
+    ImdbMovie#tagline
+    Rake task for incrementing the gem version
+    Small refactorization & added ImdbMovie#get_data
+    Using Google for searching
+    Included GemSpec
+    Updated README
+    Fixed encoding problems
+    String Extensions to unescape & recode HTML
+    - Testing against incomplete movie
+    - Handling of unkwnown data
+    - Some specs failing because of encodings
+    ImdbSearch#movies spec
+    Small refactoring
+    File reorganization
+    File reorganization
+    Small spec refactorization
+    ImdbMovie#plot
+    ImdbMovie#release_date
+    ImdbMovie#length
+    README with specs
+    ImdbMovie#company + ImdbMovie#photos
+    ImdbMovie#color
+    ImdbMovie#languages
+    ImdbMovie#countries + small fixes
+    ImdbMovie#genres
+    ImdbMovie#writers
+    ImdbMovie#cast_members
+    Specified ImdbMovie (and some implementation, but there are pending issues)
+    Some fixes
+    Git ignores
+    Updated paths
+    Directory organization
+    Specs refactoring
+    Specified ImdbSearch
+    Some tests & fixes
+    Hpricot searching
+    First version

data/README

@@ -110,6 +110,6 @@ ImdbProfile
 - should load from a file if a :filespec option is passed and the file exists
 - should not load from a file if a :filespec option is passed and the file does not exists
 
-Finished in 9.20481 seconds
+Finished in 9.302841 seconds
 
 85 examples, 0 failures

data/Rakefile

@@ -0,0 +1,96 @@
+require 'rubygems'
+require 'rake'
+require 'spec/rake/spectask'
+
+desc "Run all specs"
+task :default => :spec
+
+#desc "Run all specs"
+#Spec::Rake::SpecTask.new('spec') do |t|
+#  t.spec_files = FileList['spec/**/*.rb']
+#end
+#
+#desc "Run all specs and generate HTML report"
+#Spec::Rake::SpecTask.new('spec:html') do |t|
+#  t.spec_files = FileList['spec/**/*.rb']
+#  t.spec_opts = ["--format", "html:spec.html"]
+#end
+#
+#desc "Run all specs and dump the result to README"
+#Spec::Rake::SpecTask.new('spec:readme') do |t|
+#  t.spec_files = FileList['spec/**/*.rb']
+#  t.spec_opts = ["--format", "specdoc:README"]
+#end
+
+
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new('spec:html') do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+  spec.spec_opts = ["--format", "html:spec.html"]
+end
+
+Spec::Rake::SpecTask.new('spec:readme') do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+  spec.spec_opts = ["--format", "specdoc:README"]
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+
+#namespace :gem do
+#  desc "Increments the Gem version in imdb.gemspec"
+#  task :increment do
+#    lines = File.new('imdb.gemspec').readlines
+#    lines.each do |line|
+#      next unless line =~ /version = '\d+\.\d+\.(\d+)'/
+#      line.gsub!(/\d+'/, "#{$1.to_i + 1}'")
+#    end
+#    File.open('imdb.gemspec', 'w') do |f|
+#      lines.each do |line|
+#        f.write(line)
+#      end
+#    end
+#  end
+#end
+
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "imdb"
+    gem.summary = %Q{TODO}
+    gem.email = "roy@wright.org"
+    gem.homepage = "http://github.com/royw/imdb"
+    gem.authors = ["Roy Wright"]
+    gem.files.reject! { |fn| File.basename(fn) =~ /^tt\d+\.html/}
+
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+rescue LoadError
+  puts "Jeweler not available. Install it with: sudo gem install technicalpickles-jeweler -s http://gems.github.com"
+end
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "imdb #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION.yml

@@ -0,0 +1,4 @@
+--- 
+:minor: 0
+:patch: 19
+:major: 0

data/lib/imdb/imdb_profile.rb

@@ -0,0 +1,277 @@
+# This is the model for the IDMB profile which is used
+# to find ImdbMovie meta data from either online or from
+# a cached file.
+#
+# Usage:
+#
+# profiles = ImdbProfile.all(:titles => ['The Alamo'])
+#
+# profile = ImdbProfile.first(:imdb_id => 'tt0123456')
+# or
+# profile = ImdbProfile.first(:titles => ['movie title 1', 'movie title 2',...]
+#                             :media_years => ['2000'],
+#                             :production_years => ['1999'],
+#                             :released_years => ['2002', '2008']
+#                             :filespec => media.path_to(:imdb_xml))
+# puts profile.movie['key'].first
+# puts profile.to_xml
+# puts profile.imdb_id
+#
+
+# An optional logger.
+# If initialized with a logger instance, uses the logger
+# otherwise doesn't do anything.
+# Basically trying to not require a particular logger class.
+class OptionalLogger
+  # logger may be nil or a logger instance
+  def initialize(logger)
+    @logger = logger
+  end
+
+  # debug {...}
+  def debug(&blk)
+    @logger.debug(blk.call) unless @logger.nil?
+  end
+
+  # info {...}
+  def info(&blk)
+    @logger.info(blk.call) unless @logger.nil?
+  end
+
+  # warn {...}
+  def warn(&blk)
+    @logger.warn(blk.call) unless @logger.nil?
+  end
+
+  # error {...}
+  def error(&blk)
+    @logger.error(blk.call) unless @logger.nil?
+  end
+end
+
+class ImdbProfile
+
+  # options:
+  #   :imdb_id          => String containing the IMDB ID (ex: 'tt0465234')
+  #                        Note, the leading 'tt' is optional.
+  #   :titles           => titles,
+  #   :media_years      => Array of integer, 4 digit years (ex: [1998]).
+  #                        Should be the year(s) from the media file name.
+  #                        This let's the user say what year when they name
+  #                        the file.
+  #   :production_years => Array of integer, 4 digit years (ex: [1997,1998]).
+  #                        Should be the year(s) the movie was made.
+  #                        Note, some databases differ on the production year.
+  #   :released_years   => Array of integer, 4 digit years (ex: [1998, 2008])
+  #                        Should be the year(s) the movie was released.
+  #   :logger           => Logger instance
+  # returns Array of ImdbProfile instances
+  def self.all(options={})
+    @class_logger = OptionalLogger.new(options[:logger])
+    @class_logger.debug {"ImdbProfile.all(#{options.inspect})"} unless options[:logger].nil?
+    result = []
+    if has_option?(options, :imdb_id) || (has_option?(options, :filespec) && File.exist?(options[:filespec]))
+      result << ImdbProfile.new(options[:imdb_id], options[:filespec], options[:logger])
+    elsif has_option?(options, :titles)
+      result += self.lookup(options[:titles],
+                            options[:media_years],
+                            options[:production_years],
+                            options[:released_years]
+                          ).collect{|ident| ImdbProfile.new(ident, options[:filespec], options[:logger])}
+    end
+    result
+  end
+
+  # see ImdbProfile.all for options description
+  def self.first(options={})
+    self.all(options).first
+  end
+
+  protected
+
+  def self.has_option?(options, key)
+    options.has_key?(key) && !options[key].blank?
+  end
+
+  def initialize(ident, filespec, logger)
+    @imdb_id = ident
+
+    @filespec = filespec
+    @logger = OptionalLogger.new(logger)
+    load
+  end
+
+  public
+
+  # returns the IMDB ID String
+  attr_reader :imdb_id
+
+  # returns a Hash with the movie's meta data generated from ImdbMovie.to_hash.
+  # See ImdbMovie for details.
+  attr_reader :movie
+
+  # return the xml as a String
+  def to_xml
+    xml = ''
+    unless @movie.blank?
+      @movie.delete_if { |key, value| value.nil? }
+      xml = XmlSimple.xml_out(@movie, 'NoAttr' => true, 'RootName' => 'movie')
+    end
+    xml
+  end
+
+  protected
+
+  # @movie keys => [:title, :directors, :poster_url, :tiny_poster_url, :poster,
+  #                 :rating, :cast_members, :writers, :year, :genres, :plot,
+  #                 :tagline, :aspect_ratio, :length, :release_date, :countries,
+  #                 :languages, :color, :company, :photos, :raw_title,
+  #                 :release_year, :also_known_as, :mpaa, :certifications]
+  # returns Hash or nil
+  def load
+    if !@filespec.blank? && File.exist?(@filespec)
+      @logger.debug { "loading movie filespec=> #{@filespec.inspect}" }
+      @movie = from_xml(open(@filespec).read)
+    elsif !@imdb_id.blank?
+      @logger.debug { "loading movie from imdb.com, filespec=> #{@filespec.inspect}" }
+      @movie = ImdbMovie.new(@imdb_id.gsub(/^tt/, '')).to_hash
+      @movie['id'] = 'tt' + @imdb_id.gsub(/^tt/, '') unless @movie.blank?
+      save(@filespec) unless @filespec.blank?
+    end
+    unless @movie.blank?
+      @imdb_id = @movie['id']
+      @imdb_id = @imdb_id.first if @imdb_id.respond_to?('[]') && @imdb_id.length == 1
+    else
+      @movie = nil
+    end
+  end
+
+  def from_xml(xml)
+    begin
+      movie = XmlSimple.xml_in(xml)
+    rescue Exception => e
+      @logger.warn { "Error converting from xml: #{e.to_s}" }
+      movie = nil
+    end
+    movie
+  end
+
+  def save(filespec)
+    begin
+      xml = self.to_xml
+      unless xml.blank?
+        @logger.debug { "saving #{filespec}" }
+        save_to_file(filespec, xml)
+      end
+    rescue Exception => e
+      @logger.error {"Unable to save imdb profile to #{filespec} - #{e.to_s}"}
+    end
+  end
+
+  def save_to_file(filespec, data)
+    new_filespec = filespec + '.new'
+    File.open(new_filespec, "w") do |file|
+      file.puts(data)
+    end
+    backup_filespec = filespec + '~'
+    File.delete(backup_filespec) if File.exist?(backup_filespec)
+    File.rename(filespec, backup_filespec) if File.exist?(filespec)
+    File.rename(new_filespec, filespec)
+    File.delete(new_filespec) if File.exist?(new_filespec)
+  end
+
+  # lookup IMDB title using years as the secondary search key
+  # the titles should behave as an Array, the intent here is to be
+  # able to try to find the exact title from DVD Profiler and if that
+  # fails, to try to find the title pattern
+  # The search order is:
+  # 1) media_years should be from media filename
+  # 2) production years
+  # 3) production years plus/minus a year
+  # 4) released years
+  # 5) released years plus/minus a year
+  # 6) no years
+  def self.lookup(titles, media_years, production_years, released_years)
+    idents = []
+    year_sets = []
+    year_sets << media_years unless media_years.blank?
+    year_sets << fuzzy_years(production_years, 0) unless production_years.blank?
+    year_sets << fuzzy_years(production_years, -1..1) unless production_years.blank?
+    year_sets << fuzzy_years(released_years, 0) unless released_years.blank?
+    year_sets << fuzzy_years(released_years, -1..1) unless released_years.blank?
+    year_sets << [] if media_years.blank?
+
+    titles.flatten.uniq.compact.each do |title|
+      [false, true].each do |search_akas|
+        @class_logger.debug { (search_akas ? 'Search AKAs' : 'Do not search AKAs') }
+        imdb_search = ImdbSearch.new(title, search_akas)
+        @cache ||= {}
+        imdb_search.set_cache(@cache)
+
+        if year_sets.flatten.uniq.compact.empty?
+          idents = imdb_search.movies.collect{|m| m.id.to_s}.uniq.compact
+        else
+          year_sets.each do |years|
+            new_idents = find_id(imdb_search, title, years, search_akas)
+            @class_logger.debug { "new_idents => #{new_idents.inspect}" }
+            idents += new_idents
+            break unless new_idents.blank?
+          end
+        end
+        break unless idents.blank?
+      end
+      break unless idents.blank?
+    end
+    idents.uniq.compact
+  end
+
+  # Different databases seem to mix up released versus production years.
+  # So we combine both into a Array of integer years.
+  # fuzzy is an integer range, basically expand each known year by the fuzzy range
+  # i.e., let production and released year both be 2000 and fuzzy=-1..1,
+  # then the returned years would be [1999, 2000, 2001]
+  def self.fuzzy_years(source_years, fuzzy)
+    years = []
+    unless source_years.blank?
+      years = [source_years].flatten.collect do |date|
+        a = []
+        if date.to_s =~ /(\d{4})/
+          y = $1.to_i
+          a = [*fuzzy].collect do
+            |f| y.to_i + f
+          end
+        end
+        a
+      end
+    end
+    result = years.flatten.uniq.compact.sort
+    result
+  end
+
+  # try to find the imdb id for the movie
+  def self.find_id(imdb_search, title, years, search_akas)
+    idents = []
+
+    @class_logger.info { "Searching IMDB for \"#{title}\" (#{years.join(", ")})" }
+    unless title.blank?
+      begin
+        movies = imdb_search.movies
+        @class_logger.debug { "movies => (#{movies.collect{|m| [m.id, m.year, m.title]}.inspect})"}
+        if movies.size == 1
+          idents = [movies.first.id.to_s]
+        elsif movies.size > 1
+          @class_logger.debug { "years => #{years.inspect}"}
+          same_year_movies = movies.select{ |m| !m.year.blank? && years.include?(m.year.to_i) }
+          idents = same_year_movies.collect{|m| m.id.to_s}
+          @class_logger.debug { "same_year_movies => (#{same_year_movies.collect{|m| [m.id, m.year, m.title]}.inspect})"}
+        end
+      rescue Exception => e
+        @class_logger.error { "Error searching IMDB - " + e.to_s }
+        @class_logger.error { e.backtrace.join("\n") }
+      end
+    end
+    @class_logger.debug { "IMDB id => #{idents.join(', ')}" } unless idents.blank?
+    idents
+  end
+
+end