myimdb 0.3.0

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Gaurav Sharma
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,17 @@
+= myimdb
+
+Utility gem for fetching movie details.
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2009 Gaurav Sharma. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,22 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "myimdb"
+    gem.summary = %Q{Utility gem for fetching movie details.}
+    gem.email = "gaurav@vinsol.com"
+    gem.homepage = "http://github.com/gauravs/myimdb"
+    gem.authors = ["Gaurav"]
+    gem.add_dependency 'httparty', '>= 0.4.5'
+    gem.add_dependency 'nokogiri', '>= 1.3.3'
+    gem.rubyforge_project = 'myimdb'
+    gem.files = FileList["**/*"]
+  end
+  Jeweler::RubyforgeTasks.new do |rubyforge|
+  rubyforge.doc_task = "rdoc"
+  end
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end

data/VERSION

@@ -0,0 +1 @@
+0.3.0

data/bin/myimdb

@@ -0,0 +1,34 @@
+#!/usr/bin/env ruby
+
+# point this file to a folder and all the folder inside it will be renamed
+require 'myimdb.rb'
+
+unless ARGV[0]
+  p "Source directory required - exiting"
+  exit(0)
+end
+
+file_paths = Dir["#{ARGV[0]}/*"]
+search_scope  = "imdb.com"
+
+file_paths.each do |path|
+  next if !File.directory?(path)
+  p "============================================"
+  name = File.basename(path)
+  if name.scan(/\[.*?\]/).size == 3
+    p "Skipping: #{name}"
+  else
+    p "Fetching details for: #{name}"
+    begin
+      search_result = Myimdb::Search::Google.search_text(name, search_scope)[0]
+      imdb          = Myimdb::Scraper::Imdb.new(search_result["url"])
+      new_name = name.gsub(/\[\S+\]/, "").strip
+      new_name << " [#{imdb.year}] [#{imdb.rating},#{imdb.votes}] [#{imdb.directors.join(',')}]"
+      p "Renaming: #{name} to: #{new_name}"
+      new_path = File.join(File.dirname(path), new_name)
+      File.rename(path, new_path)
+    rescue
+      p "Unable to fetch details for: #{name}"
+    end
+  end
+end

data/bin/myimdb.bat

@@ -0,0 +1 @@
+@"ruby.exe" "%~dpn0" %*

data/lib/myimdb.rb

@@ -0,0 +1,7 @@
+require 'rubygems'
+require 'httparty'
+require 'nokogiri'
+require 'open-uri'
+
+require 'myimdb/search'
+require 'myimdb/scraper'

data/lib/myimdb/scraper.rb

@@ -0,0 +1,5 @@
+require 'myimdb/scraper/string_extensions'
+require 'myimdb/scraper/base'
+require 'myimdb/scraper/imdb'
+require 'myimdb/scraper/metacritic'
+require 'myimdb/scraper/rotten_tomatoes'

data/lib/myimdb/scraper/base.rb

@@ -0,0 +1,45 @@
+class UnformattedHtml < Exception; end
+
+module HandleExceptions
+  def self.included(base)
+    base.send(:include, InstanceMethods)
+    base.send(:extend, ClassMethods)
+  end
+  
+  module InstanceMethods
+  end
+  
+  module ClassMethods
+    def handle_exceptions_for(*method_names)
+      method_names.each do |method_name|
+        alias_method("_#{method_name}", method_name)
+        define_method(method_name) do
+          begin
+            send("_#{method_name}")
+          rescue
+            raise UnformattedHtml.new("Unable to find tag: #{method_name}, probably you are parsing the wrong page.")
+          end
+        end
+      end
+    end
+  end
+end
+
+module Myimdb
+  module Scraper
+    class Base
+      include HandleExceptions
+      def year
+      end
+  
+      def tagline
+      end
+  
+      def directors
+      end
+  
+      def writers
+      end
+    end
+  end
+end

data/lib/myimdb/scraper/imdb.rb

@@ -0,0 +1,48 @@
+module Myimdb
+  module Scraper
+    class Imdb < Scraper::Base
+      def initialize(url)
+        @url = url
+      end
+    
+      def directors
+        document.css('.info h5:contains("Director") + .info-content a:not(.tn15more)').collect{ |a| a.text }
+      end
+    
+      def writers
+        document.css('.info h5:contains("Writer") + .info-content a:not(.tn15more)').collect{ |a| a.text }
+      end
+    
+      def rating
+        document.css(".general.rating b").inner_text.strip.split('/').first.to_f
+      end
+    
+      def votes
+        document.css(".general.rating a").inner_text.strip.sub(',', '').to_i
+      end
+    
+      def genres
+        document.css('.info h5:contains("Genre:") + .info-content a:not(.tn15more)').collect{ |a| a.text }
+      end
+    
+      def tagline
+        document.css('.info h5:contains("Tagline:") + .info-content').children[0].text.strip
+      end
+    
+      def plot
+        document.css('.info h5:contains("Plot:") + .info-content').children[0].text.strip
+      end
+    
+      def year
+        document.css("div#tn15title a:first")[0].text.to_i
+      end
+    
+      private
+        def document
+          @document ||= Nokogiri::HTML(open(@url))
+        end
+        
+        handle_exceptions_for :directors, :writers, :rating, :votes, :genres, :tagline, :plot, :year
+    end
+  end
+end

data/lib/myimdb/scraper/metacritic.rb

@@ -0,0 +1,32 @@
+module Myimdb
+  module Scraper
+    class Metacritic < Scraper::Base
+      def initialize(url)
+        @url = url
+      end
+    
+      def rating
+        document.css("#metascore").inner_text.strip.to_f/10
+      end
+    
+      def votes
+        document.at("a[@href='#critics']").inner_text.strip.to_i
+      end
+    
+      def genres
+        document.css("#productinfo p:first").text.gsub(/^\S+:/, '').split("|").map(&:strip_useless_chars)
+      end
+    
+      def plot
+        document.css("#productsummary .summarytext").inner_text.strip
+      end
+    
+      private
+        def document
+          @document ||= Nokogiri::HTML(open(@url))
+        end
+        
+        handle_exceptions_for :rating, :votes, :genres, :plot
+    end
+  end
+end

data/lib/myimdb/scraper/rotten_tomatoes.rb

@@ -0,0 +1,32 @@
+module Myimdb
+  module Scraper
+    class RottenTomatoes < Scraper::Base
+      def initialize(url)
+        @url = url
+      end
+
+      def rating
+        document.css("#tomatometer_data p:nth-child(4) span").inner_text.strip.to_i
+      end
+    
+      def votes
+        document.css("#tomatometer_data p:nth-child(1) span").inner_text.strip.to_i
+      end
+    
+      def genres
+        document.css("#movie_stats .fl:first p:last .content a").inner_text.scraper_unescape_html.to_a
+      end
+    
+      def plot
+        document.css("#movie_synopsis_all").inner_text.strip
+      end
+    
+      private
+        def document
+          @document ||= Nokogiri::HTML(open(@url))
+        end
+        
+        handle_exceptions_for :rating, :votes, :genres, :plot
+    end
+  end
+end

data/lib/myimdb/scraper/string_extensions.rb

@@ -0,0 +1,22 @@
+require 'cgi'
+require 'iconv'
+
+module Myimdb
+  module Scraper
+    module StringExtensions
+      def scraper_unescape_html
+        Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(self))
+      end
+
+      def scraper_strip_tags
+        gsub(/<\/?[^>]*>/, "")
+      end
+    
+      def strip_useless_chars
+        gsub(/[^a-zA-z0-9\|\-_\(\)@$\/\\]/, '')
+      end
+    end
+  end
+end
+
+String.send :include, Myimdb::Scraper::StringExtensions

data/lib/myimdb/search.rb

@@ -0,0 +1,2 @@
+require 'httparty'
+require 'myimdb/search/google'

data/lib/myimdb/search/google.rb

@@ -0,0 +1,17 @@
+module Myimdb
+  module Search
+    class Google
+      include HTTParty
+
+      format    :json
+      headers   'Content-Type' => 'application/json' 
+      base_uri  'ajax.googleapis.com'
+    
+      def self.search_text( text, restrict_to=nil )
+        text = "site:#{restrict_to} #{text}" if restrict_to
+        response = get( '/ajax/services/search/web', :query=> {:v=> '1.0', :q=> text} )
+        response['responseData'] and response['responseData']['results']
+      end
+    end
+  end
+end

data/myimdb.gemspec

@@ -0,0 +1,70 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{myimdb}
+  s.version = "0.3.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Gaurav"]
+  s.date = %q{2009-12-28}
+  s.email = %q{gaurav@vinsol.com}
+  s.executables = ["myimdb", "myimdb.bat"]
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "bin/myimdb",
+     "bin/myimdb.bat",
+     "lib/myimdb.rb",
+     "lib/myimdb/scraper.rb",
+     "lib/myimdb/scraper/base.rb",
+     "lib/myimdb/scraper/imdb.rb",
+     "lib/myimdb/scraper/metacritic.rb",
+     "lib/myimdb/scraper/rotten_tomatoes.rb",
+     "lib/myimdb/scraper/string_extensions.rb",
+     "lib/myimdb/search.rb",
+     "lib/myimdb/search/google.rb",
+     "myimdb.gemspec",
+     "pkg/myimdb-0.0.0.gem",
+     "pkg/myimdb-0.1.0.gem",
+     "pkg/myimdb-0.2.0.gem",
+     "pkg/myimdb-0.3.0.gem",
+     "test/helper.rb",
+     "test/test_myimdb.rb"
+  ]
+  s.homepage = %q{http://github.com/gauravs/myimdb}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{myimdb}
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Utility gem for fetching movie details.}
+  s.test_files = [
+    "test/helper.rb",
+     "test/test_myimdb.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<httparty>, [">= 0.4.5"])
+      s.add_runtime_dependency(%q<nokogiri>, [">= 1.3.3"])
+    else
+      s.add_dependency(%q<httparty>, [">= 0.4.5"])
+      s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
+    end
+  else
+    s.add_dependency(%q<httparty>, [">= 0.4.5"])
+    s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
+  end
+end
+

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'myimdb'
+
+class Test::Unit::TestCase
+end

data/test/test_myimdb.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestMyimdb < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification 
+name: myimdb
+version: !ruby/object:Gem::Version 
+  version: 0.3.0
+platform: ruby
+authors: 
+- Gaurav
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-12-28 00:00:00 +05:30
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: httparty
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.4.5
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.3.3
+    version: 
+description: 
+email: gaurav@vinsol.com
+executables: 
+- myimdb
+- myimdb.bat
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- bin/myimdb
+- bin/myimdb.bat
+- lib/myimdb.rb
+- lib/myimdb/scraper.rb
+- lib/myimdb/scraper/base.rb
+- lib/myimdb/scraper/imdb.rb
+- lib/myimdb/scraper/metacritic.rb
+- lib/myimdb/scraper/rotten_tomatoes.rb
+- lib/myimdb/scraper/string_extensions.rb
+- lib/myimdb/search.rb
+- lib/myimdb/search/google.rb
+- myimdb.gemspec
+- pkg/myimdb-0.0.0.gem
+- pkg/myimdb-0.1.0.gem
+- pkg/myimdb-0.2.0.gem
+- pkg/myimdb-0.3.0.gem
+- test/helper.rb
+- test/test_myimdb.rb
+has_rdoc: true
+homepage: http://github.com/gauravs/myimdb
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: myimdb
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Utility gem for fetching movie details.
+test_files: 
+- test/helper.rb
+- test/test_myimdb.rb