royw-imdb 0.0.17 → 0.0.19

data/spec/cache_extensions.rb

@@ -0,0 +1,91 @@
+# NOTE extremely ugly and non-DRY.  Probably good candidate for meta programming.
+
+# override the classes' read_page method and replace with one
+# that will cache pages in spec/samples/{url}
+
+class ImdbMovie
+  private
+  def read_page(page)
+    html = nil
+    filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+    if File.exist?(filespec)
+      html = open(filespec).read
+    else
+      html = open(page).read
+      cache_html_files(page, html)
+    end
+    html
+  end
+
+  # this is used to save imdb pages so they may be used by rspec
+  def cache_html_files(page, html)
+    begin
+      filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+      unless File.exist?(filespec)
+        puts "caching #{filespec}"
+        File.mkdirs(File.dirname(filespec))
+        File.open(filespec, 'w') { |f| f.puts html }
+      end
+    rescue Exception => eMsg
+      puts eMsg.to_s
+    end
+  end
+end
+
+class ImdbSearch
+  private
+  def read_page(page)
+    html = nil
+    filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+    if File.exist?(filespec)
+      html = open(filespec).read
+    else
+      html = open(page).read
+      cache_html_files(page, html)
+    end
+    html
+  end
+
+  # this is used to save imdb pages so they may be used by rspec
+  def cache_html_files(page, html)
+    begin
+      filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+      unless File.exist?(filespec)
+        puts "caching #{filespec}"
+        File.mkdirs(File.dirname(filespec))
+        File.open(filespec, 'w') { |f| f.puts html }
+      end
+    rescue Exception => eMsg
+      puts eMsg.to_s
+    end
+  end
+end
+
+class ImdbImage
+  private
+  def read_page(page)
+    html = nil
+    filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+    if File.exist?(filespec)
+      html = open(filespec).read
+    else
+      html = open(page).read
+      cache_html_files(page, html)
+    end
+    html
+  end
+
+  # this is used to save imdb pages so they may be used by rspec
+  def cache_html_files(page, html)
+    begin
+      filespec = page.gsub(/^http:\//, 'spec/samples').gsub(/\/$/, '.html')
+      unless File.exist?(filespec)
+        puts "caching #{filespec}"
+        File.mkdirs(File.dirname(filespec))
+        File.open(filespec, 'w') { |f| f.puts html }
+      end
+    rescue Exception => eMsg
+      puts eMsg.to_s
+    end
+  end
+end

data/spec/imdb_image_spec.rb

@@ -0,0 +1,23 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe ImdbMovie do
+
+  describe 'Indiana Jones and the Last Crusade' do
+
+    before(:each) do
+      @imdb_image = ImdbImage.new("/rg/action-box-title/primary-photo/media/rm1203608832/tt0097576")
+#       @imdb_image.stub!(:open).and_return(open("#{$samples_dir}/sample_image.html"))
+    end
+
+#     it "should query IMDB url" do
+#       @imdb_image.should_receive(:open).with("http://www.imdb.com/rg/action-box-title/primary-photo/media/rm1203608832/tt0097576").and_return(open("#{$samples_dir}/sample_image.html"))
+#       @imdb_image.send(:document)
+#     end
+
+    it "should get the image" do
+      @imdb_image.image.should == "http://ia.media-imdb.com/images/M/MV5BMTkzODA5ODYwOV5BMl5BanBnXkFtZTcwMjAyNDYyMQ@@._V1._SX216_SY316_.jpg"
+    end
+
+  end
+
+end

data/spec/imdb_movie_spec.rb

@@ -0,0 +1,232 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe ImdbMovie do
+
+  describe 'Jet Pilot' do
+
+    before(:each) do
+      @imdb_movie = ImdbMovie.new('0050562')
+      @imdb_movie.stub!(:open).and_return(open("#{$samples_dir}/sample_jet_pilot.html"))
+    end
+
+    it "should query IMDB url" do
+#       @imdb_movie.should_receive(:open).with("http://www.imdb.com/title/tt0050562/").and_return(open("#{$samples_dir}/sample_jet_pilot.html"))
+      @imdb_movie.should_receive(:fetch).with("http://www.imdb.com/title/tt0050562/").and_return(open("#{$samples_dir}/www.imdb.com/title/tt0050562.html"))
+      @imdb_movie.send(:document)
+    end
+
+    it "should convert to xml" do
+      xml = @imdb_movie.to_xml
+      xml.should =~ /<year>1957<\/year>/
+    end
+
+    it "should convert to yaml" do
+      yaml = @imdb_movie.to_yaml
+      yaml.should =~ /year: "1957"/
+    end
+
+  end
+
+  describe 'Indiana Jones and the Last Crusade' do
+
+    before(:each) do
+      @imdb_movie = ImdbMovie.new('0097576')
+#       @imdb_movie.stub!(:open).and_return(open("#{$samples_dir}/sample_movie.html"))
+    end
+
+#     it "should query IMDB url" do
+#       @imdb_movie.should_receive(:open).with("http://www.imdb.com/title/tt0097576/").and_return(open("#{$samples_dir}/www.imdb.com/title/tt0097576.html"))
+#       @imdb_movie.send(:document)
+#     end
+
+    it "should get the title" do
+      @imdb_movie.title.should == "Indiana Jones and the Last Crusade"
+    end
+
+    it "should get director(s)" do
+      @imdb_movie.directors.should include('Steven Spielberg')
+    end
+
+    it "should get the poster url" do
+      @imdb_movie.poster_url.should == "/rg/action-box-title/primary-photo/media/rm1203608832/tt0097576"
+    end
+
+    it "should return an ImdbImage object" do
+      @imdb_movie.poster.should be_instance_of(ImdbImage)
+    end
+
+    it "should get the rating" do
+      @imdb_movie.rating.should == 8.3
+    end
+
+    it "should get cast members" do
+      @imdb_movie.cast_members.should include(['Harrison Ford', 'Indiana Jones'])
+      @imdb_movie.cast_members.should include(['Sean Connery', 'Professor Henry Jones'])
+      @imdb_movie.cast_members.should include(['Denholm Elliott', 'Dr. Marcus Brody'])
+      @imdb_movie.cast_members.should include(['Alison Doody', 'Dr. Elsa Schneider'])
+      @imdb_movie.cast_members.should include(['John Rhys-Davies', 'Sallah'])
+      @imdb_movie.cast_members.should_not include('more')
+    end
+
+    it "should get the writers" do
+      @imdb_movie.writers.should include('George Lucas')
+      @imdb_movie.writers.should include('Philip Kaufman')
+      @imdb_movie.writers.should_not include('more')
+    end
+
+    it "should get the year" do
+      @imdb_movie.year.should == "1989"
+    end
+
+    it "should get the release date" do
+      @imdb_movie.release_date.should be_an_instance_of(Date)
+      @imdb_movie.release_date.to_s.should == Date.new(1989, 5, 24).to_s
+    end
+
+    it "should get the genres" do
+      @imdb_movie.genres.should have(2).strings
+      @imdb_movie.genres.should include('Action')
+      @imdb_movie.genres.should include('Adventure')
+    end
+
+    it "should get the plot" do
+      @imdb_movie.plot.should == "When Dr. Henry Jones Sr. suddenly goes missing while pursuing the Holy Grail, eminent archaeologist Indiana Jones must follow in his father's footsteps and stop the Nazis."
+    end
+
+    it "should get the length" do
+      @imdb_movie.length.should == '127 min'
+    end
+
+    it "should get the countries" do
+      @imdb_movie.countries.should have(1).string
+      @imdb_movie.countries.should include('USA')
+    end
+
+    it "should get the languages" do
+      @imdb_movie.languages.should have(3).strings
+      @imdb_movie.languages.should include('English')
+      @imdb_movie.languages.should include('German')
+      @imdb_movie.languages.should include('Greek')
+    end
+
+    it "should get the color" do
+      @imdb_movie.color.should == 'Color'
+    end
+
+    it "should get the company" do
+      @imdb_movie.company.should == 'Lucasfilm'
+    end
+
+    it "should get some photos" do
+      @imdb_movie.photos.should have(10).strings
+      @imdb_movie.photos.should include('http://ia.media-imdb.com/images/M/MV5BMTY4MzY3OTY0MF5BMl5BanBnXkFtZTYwODM0OTE3._V1._CR82,0,320,320_SS90_.jpg')
+      @imdb_movie.photos.should include('http://ia.media-imdb.com/images/M/MV5BMjAwNTM4ODc3Nl5BMl5BanBnXkFtZTYwNzU0OTE3._V1._CR82,0,320,320_SS90_.jpg')
+    end
+
+    it "should get the tagline" do
+      @imdb_movie.tagline.should == "He's back in an all new adventure. Memorial Day 1989."
+    end
+
+    it "should get the aspect ratio" do
+      @imdb_movie.aspect_ratio.should == "2.20 : 1"
+    end
+
+    it "should convert to xml" do
+      xml = @imdb_movie.to_xml
+      xml.should =~ /<year>1989<\/year>/
+    end
+
+    it "should convert to yaml" do
+      yaml = @imdb_movie.to_yaml
+      yaml.should =~ /year: "1989"/
+    end
+
+    it "should be able to convert to and then from xml" do
+      hash = nil
+      begin
+        xml = @imdb_movie.to_xml
+        hash = XmlSimple.xml_in(xml)
+      rescue
+        hash = nil
+      end
+      hash.should_not be_nil
+    end
+  end
+
+  describe 'Han robado una estrella' do
+
+    before(:each) do
+      @imdb_movie = ImdbMovie.new('0054961')
+#       @imdb_movie.stub!(:open).and_return(open("#{$samples_dir}/sample_incomplete_movie.html"))
+    end
+
+#     it "should query IMDB url" do
+#       @imdb_movie.should_receive(:open).with("http://www.imdb.com/title/tt0054961/").and_return(open("#{$samples_dir}/sample_incomplete_movie.html"))
+#       @imdb_movie.should_receive(:open).with("http://www.imdb.com/title/tt0054961/").and_return(open("#{$samples_dir}/www.imdb.com/title/tt0054961.html"))
+#       @imdb_movie.send(:document)
+#     end
+
+    it "should get the title" do
+      @imdb_movie.title.should == "Han robado una estrella"
+    end
+
+    it "should get director(s)" do
+      @imdb_movie.directors.should include('Javier Setó')
+    end
+
+    it "should not get the poster" do
+      @imdb_movie.poster.should be_nil
+    end
+
+    it "should get cast members" do
+      @imdb_movie.cast_members.should include(['Rafaela Aparicio', ''])
+      @imdb_movie.cast_members.should include(['Marujita Díaz', ''])
+      @imdb_movie.cast_members.should include(['Espartaco Santoni', ''])
+      @imdb_movie.cast_members.should_not include('more')
+    end
+
+    it "should get the writers" do
+      @imdb_movie.writers.should have(1).string
+      @imdb_movie.writers.should include('Paulino Rodrigo')
+    end
+
+    it "should get the release date" do
+      @imdb_movie.release_date.should be_an_instance_of(Date)
+      @imdb_movie.release_date.should == Date.new(1963, 9, 9)
+    end
+
+    it "should get the genres" do
+      @imdb_movie.genres.should == ['Comedy', 'Musical']
+    end
+
+    it "should not get the plot" do
+      @imdb_movie.plot.should be_nil
+    end
+
+    it "should get the length" do
+      @imdb_movie.length.should == '93 min'
+    end
+
+    it "should get the countries" do
+      @imdb_movie.countries.should == ['Spain']
+    end
+
+    it "should get the languages" do
+      @imdb_movie.languages.should == ['Spanish']
+    end
+
+    it "should not get the color" do
+      @imdb_movie.color.should be_nil
+    end
+
+    it "should get the company" do
+      @imdb_movie.company.should == 'Brepi Films'
+    end
+
+    it "should not get any photos" do
+      @imdb_movie.photos.should be_empty
+    end
+
+  end
+
+end

data/spec/imdb_profile_spec.rb

@@ -0,0 +1,182 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+require 'tempfile'
+
+TMPDIR = File.join(File.dirname(__FILE__), '../tmp')
+
+# Time to add your specs!
+# http://rspec.info/
+
+describe "ImdbProfile" do
+
+  before(:all) do
+    File.mkdirs(TMPDIR)
+  end
+
+  after(:each) do
+    Dir.glob(File.join(TMPDIR, "imdb_profile_spec*")).each { |filename| File.delete(filename) }
+  end
+
+  it "should find by imdb_id that is prefixed with a 'tt'" do
+    profile = ImdbProfile.first(:imdb_id => 'tt0465234')
+    profile.should_not == nil
+  end
+
+  it "should find by imdb_id that is not prefixed with 'tt'" do
+    profile = ImdbProfile.first(:imdb_id => '0465234')
+    profile.should_not == nil
+  end
+
+  it "should find by single title" do
+    profile = ImdbProfile.first(:titles => ['National Treasure: Book of Secrets'])
+    profile.should_not == nil
+  end
+
+  it "should find by multiple title" do
+    profile = ImdbProfile.first(:titles => ['National Treasure: Book of Secrets', 'National Treasure 2'])
+    profile.should_not == nil
+  end
+
+  it "should find by multiple title embedded in arrays" do
+    profile = ImdbProfile.first(:titles => [['National Treasure: Book of Secrets'], 'National Treasure 2'])
+    profile.should_not == nil
+  end
+
+  it "should find by AKA title" do
+    profile = ImdbProfile.first(:titles => ['National Treasure 2'])
+    profile.should_not == nil
+  end
+
+  # We use two versions of "The Alamo" to test for year discrimination
+  #  John Wayne's The Alamo produced and released in 1960, IMDB ID => tt0053580
+  #  John Lee Hancock's The Alamo produced and released in 2004, IMDB ID => tt0318974
+
+  # test all()
+  it "should find multiple versions of The Alamo" do
+    profiles = ImdbProfile.all(:titles => ['The Alamo'])
+    profiles.length.should > 1
+  end
+
+  it "should find the two versions of The Alamo that we are interested in" do
+    profiles = ImdbProfile.all(:titles => ['The Alamo'])
+    imdb_ids = profiles.collect{|profile| profile.imdb_id}
+    imdb_ids = imdb_ids.select{|ident| ident == 'tt0053580' || ident == 'tt0318974'}
+    imdb_ids.uniq.compact.length.should == 2
+  end
+
+  # find first using title and media year
+
+  it "should find John Wayne's The Alamo by title with media year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :media_years => [1960])
+    profile.imdb_id.should == 'tt0053580'
+  end
+
+  it "should find John Lee Hancock's The Alamo by title with media year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :media_years => [2004])
+    profile.imdb_id.should == 'tt0318974'
+  end
+
+  # find first using title and production year
+
+  it "should find John Wayne's The Alamo by title with production year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [1960])
+    profile.imdb_id.should == 'tt0053580'
+  end
+
+  it "should find John Lee Hancock's The Alamo by title with production year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [2004])
+    profile.imdb_id.should == 'tt0318974'
+  end
+
+  # find first using title and released year
+
+  it "should find John Wayne's The Alamo by title with released year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1960])
+    profile.imdb_id.should == 'tt0053580'
+  end
+
+  it "should find John Lee Hancock's The Alamo by title with released year" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [2004])
+    profile.imdb_id.should == 'tt0318974'
+  end
+
+  # here we test fuzzy year matching (plus or minus a year)
+  # fuzzy years are only supported for production and released years, not media years
+
+  it "should not find John Wayne's The Alamo by title with the media year off by a year" do
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :media_years => [1959])
+    profile2 = ImdbProfile.first(:titles => ['The Alamo'], :media_years => [1961])
+    (profile1.should be_nil) && (profile2.should be_nil)
+  end
+
+  it "should find John Wayne's The Alamo by title with the production year off by a year" do
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [1959])
+    profile2 = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [1961])
+    (profile1.imdb_id.should == 'tt0053580') && (profile2.imdb_id.should == 'tt0053580')
+  end
+
+  it "should find John Wayne's The Alamo by title with the released year off by a year" do
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1959])
+    profile2 = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1961])
+    (profile1.imdb_id.should == 'tt0053580') && (profile2.imdb_id.should == 'tt0053580')
+  end
+
+  it "should not find John Wayne's The Alamo by title with the production year off by two years" do
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [1958])
+    profile2 = ImdbProfile.first(:titles => ['The Alamo'], :production_years => [1962])
+    (profile1.should be_nil) && (profile2.should be_nil)
+  end
+
+  it "should not find John Wayne's The Alamo by title with the released year off by two years" do
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1958])
+    profile2 = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1962])
+    (profile1.should be_nil) && (profile2.should be_nil)
+  end
+
+  # let's make sure the generated xml from to_xml() is valid
+
+  it "should be able to convert to xml and then from xml" do
+    hash = nil
+    begin
+      profile = ImdbProfile.first(:imdb_id => 'tt0465234')
+      xml = profile.to_xml
+      hash = XmlSimple.xml_in(xml)
+    rescue
+      hash = nil
+    end
+    hash.should_not be_nil
+  end
+
+  # now let's test caching the profile to/from a file
+
+  it "should not create a file if a :filespec option is passed that is nil" do
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1960], :filespec => nil)
+    Dir.glob(File.join(TMPDIR, "imdb_profile_spec*")).empty?.should be_true
+  end
+
+  it "should create a file if a :filespec option is passed" do
+    filespec = get_temp_filename
+    profile = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1960], :filespec => filespec)
+    (File.exist?(filespec) && (File.size(filespec) > 0)).should be_true
+  end
+
+  it "should load from a file if a :filespec option is passed and the file exists" do
+    filespec = get_temp_filename
+    profile1 = ImdbProfile.first(:titles => ['The Alamo'], :released_years => [1960], :filespec => filespec)
+    profile2 = ImdbProfile.first(:filespec => filespec)
+    profile1.imdb_id.should == profile2.imdb_id
+  end
+
+  it "should not load from a file if a :filespec option is passed and the file does not exists" do
+    filespec = get_temp_filename
+    profile = ImdbProfile.first(:filespec => filespec)
+    profile.should be_nil
+  end
+
+  def get_temp_filename
+    outfile = Tempfile.new('imdb_profile_spec', TMPDIR)
+    filespec = outfile.path
+    outfile.unlink
+    filespec
+  end
+end