imdb 0.7.0 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ca782282c0207181d57c8732b2028c46e91854fa
-  data.tar.gz: 93857f4686f71950e2bbb514805e87ab0c075de4
+  metadata.gz: 2c84d21278933772df9156ec48a141b0d7b7375e
+  data.tar.gz: 1f54dd630b773de99a1703ad8fbeb379a7d5cbf3
 SHA512:
-  metadata.gz: b64b0288a5ee43eced42d0fe5ebbd6d4f9d4057d3941924f08399e8235a3467d4f950c5186e58b1f1deee95f90413b74b2dc9cfa295f9763c0f7e33ccf093618
-  data.tar.gz: 423bb452e2c11f1c74925c5ff591cc1fb11ed197242f65284166e6f2b9864106efcfcdb49648ec0064e313d3b4f697cfbd24b8fe399ed74206eee08f9054a1e9
+  metadata.gz: ca8f765c422677819391031671bbd0467c7a280511435dda5eee4426f8291b6809c014d63c9662ff89813cb04a065c6a64e62ef4eae60b878a15e9a60ecd2bcd
+  data.tar.gz: c6e895315a23977569618ee9448128ebca33290568e94909241e4b2be81ca8e74ad95145a6f1f6d0d1ef3fd4c8cf3a525e905458ea2dec0778660b5139f53903

data/.travis.yml

@@ -6,12 +6,18 @@ notifications:
 rvm:
   - 1.9.2
   - 1.9.3
+  - 2.0.0
   - ruby-head
   - rbx-19mode
+  - 1.8.7
+  - ree
 
 matrix:
   allow_failures:
     - rvm: rbx-19mode
+    - rvm: ruby-head
+    - rvm: 1.8.7
+    - rvm: ree
 
 script:
   - "bundle exec rake spec"

data/MIT-LICENSE

@@ -0,0 +1,21 @@
+Copyright (c) 2009-2013 Ariejan de Vroom
+
+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.md

@@ -0,0 +1,97 @@
+# imdb [![Build Status](https://travis-ci.org/ariejan/imdb.png?branch=master)](https://travis-ci.org/ariejan/imdb)
+
+* [Sources](https://github.com/ariejan/imdb)
+* [Issues](https://github.com/ariejan/imdb/issues)
+
+## Description
+
+This gem allows you to easy access publicly available data from IMDB.
+
+## Features
+
+IMDB currently features the following:
+
+* Querying details movie info
+* Searching for movies
+* Command-line utility included.
+
+## Synopsis
+
+### Movies:
+
+    i = Imdb::Movie.new("0095016")
+
+    i.title
+    #=> "Die Hard"
+
+    i.cast_members.first
+    #=> "Bruce Willis"
+
+### Series:
+
+    serie = Imdb::Serie.new("1520211")
+
+    serie.title
+    #=> "\"The Walking Dead\""
+
+    serie.rating
+    #=> 8.8
+
+    serie.seasons.size
+    #=> 3
+
+    serie.seaon(1).episodes.size
+    #=> 6
+
+    series.season(1).episode(2).title
+    #=> "Guts"
+
+### Searching:
+
+    i = Imdb::Search.new("Star Trek")
+
+    i.movies.size
+    #=> 97
+
+### Using the command line utility is quite easy:
+
+    $ imdb Star Trek
+
+or get movie info
+
+    $ imdb 0095016
+
+## Installation
+
+    gem install imdb
+
+## Running Tests
+
+You'll need rspec and fakeweb installed to run the specs.
+
+    $ bundle install
+    $ bundle exec rake spec
+
+Although not recommended, you may run the specs against the live imdb.com 
+website. This will make a lot of calls to imdb.com, use it wisely.
+
+    $ LIVE_TEST=true bundle exec rake spec
+
+To update the packaged fixtures files with actual imdb.com samples, use the 
+`fixtures:refresh` rake task
+
+    $ bundle exec rake fixtures:refresh
+
+## Disclaimer
+
+I, or any developer who contributed to this project, accepts any kind of 
+liabilty for your use of this library.
+
+IMDB does not permit use of its data by third parties without their consent.
+
+Using this library for anything other than limited personal use may result
+in an IP ban to the IMDB website.
+
+## License
+
+See [MIT-LICENSE](https://github.com/ariejan/imdb/blob/master/MIT-LICENSE)

data/imdb.gemspec

@@ -19,7 +19,7 @@ Gem::Specification.new do |s|
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
 
-  s.add_dependency 'hpricot', '~> 0.8.6'
+  s.add_dependency 'nokogiri', '>= 1.6.0'
 
   s.add_development_dependency 'rake', '~> 10.0.3'
   s.add_development_dependency 'rspec', '~> 2.13.0'

data/lib/imdb.rb

@@ -3,7 +3,7 @@ $:.unshift(File.dirname(__FILE__)) unless
 
 require 'open-uri'
 require 'rubygems'
-require 'hpricot'
+require 'nokogiri'
 
 require 'imdb/base'
 require 'imdb/movie'

data/lib/imdb/base.rb

@@ -20,7 +20,7 @@ module Imdb
 
     # Returns an array with cast members
     def cast_members
-      document.search("table.cast td.nm a").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+      document.search("table.cast td.nm a").map { |link| link.content.strip } rescue []
     end
 
     def cast_member_ids
@@ -29,7 +29,7 @@ module Imdb
 
     # Returns an array with cast characters
     def cast_characters
-      document.search("table.cast td.char").map { |link| link.innerText } rescue []
+      document.search("table.cast td.char").map { |link| link.content.strip } rescue []
     end
 
     # Returns an array with cast members and characters
@@ -40,58 +40,58 @@ module Imdb
         memb_char[i] = "#{self.cast_members[i]} #{sep} #{self.cast_characters[i]}"
         i=i+1
       }
-      return memb_char
+      memb_char
     end
 
     # Returns the name of the director
     def director
-      document.search("h5[text()^='Director'] ~ a").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+      document.search("h5[text()^='Director'] ~ div a").map { |link| link.content.strip } rescue []
     end
 
     # Returns the url to the "Watch a trailer" page
     def trailer_url
-      'http://imdb.com' + document.at("a[@href*=/video/screenplay/]")["href"] rescue nil
+      'http://imdb.com' + document.at("a[@href*='/video/screenplay/']")["href"] rescue nil
     end
 
     # Returns an array of genres (as strings)
     def genres
-      document.search("h5[text()='Genre:'] ~ a[@href*=/Sections/Genres/']").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+      document.search("h5[text()='Genre:'] ~ div a[@href*='/Sections/Genres/']").map { |link| link.content.strip } rescue []
     end
 
     # Returns an array of languages as strings.
     def languages
-      document.search("h5[text()='Language:'] ~ a[@href*=/language/']").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+      document.search("h5[text()='Language:'] ~ div a[@href*='/language/']").map { |link| link.content.strip } rescue []
     end
 
     # Returns an array of countries as strings.
     def countries
-      document.search("h5[text()='Country:'] ~ a[@href*=/country/']").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+      document.search("h5[text()='Country:'] ~ div a[@href*='/country/']").map { |link| link.content.strip } rescue []
     end
 
     # Returns the duration of the movie in minutes as an integer.
     def length
-      document.search("//h5[text()='Runtime:']/..").innerHTML[/\d+ min/].to_i rescue nil
+      document.at("h5[text()='Runtime:'] ~ div").content[/\d+ min/].to_i rescue nil
     end
 
     # Returns the company
     def company
-      document.search("h5[text()='Company:'] ~ a[@href*=/company/']").map { |link| link.innerHTML.strip.imdb_unescape_html }.first rescue nil
+      document.search("h5[text()='Company:'] ~ div a[@href*='/company/']").map { |link| link.content.strip }.first rescue nil
     end
 
     # Returns a string containing the plot.
     def plot
-      sanitize_plot(document.search("h5[text()='Plot:'] ~ div").first.innerHTML) rescue nil
+      sanitize_plot(document.at("h5[text()='Plot:'] ~ div").content) rescue nil
     end
 
     # Returns a string containing the plot summary
     def plot_synopsis
-      doc = Hpricot(Imdb::Movie.find_by_id(@id, :synopsis))
-      doc.search("div[@id='swiki.2.1']").innerHTML.strip.imdb_unescape_html.imdb_strip_tags rescue nil
+      doc = Nokogiri::HTML(Imdb::Movie.find_by_id(@id, :synopsis))
+      doc.at("div[@id='swiki.2.1']").content.strip rescue nil
     end
 
     def plot_summary
-      doc = Hpricot(Imdb::Movie.find_by_id(@id, :plotsummary))
-      doc.search("p[@class='plotpar']").first.innerHTML.gsub(/<i.*/im, '').strip.imdb_unescape_html rescue nil
+      doc = Nokogiri::HTML(Imdb::Movie.find_by_id(@id, :plotsummary))
+      doc.at("p.plotSummary").inner_html.gsub(/<i.*/im, '').strip.imdb_unescape_html rescue nil
     end
 
     # Returns a string containing the URL to the movie poster.
@@ -107,22 +107,22 @@ module Imdb
 
     # Returns a float containing the average user rating
     def rating
-      document.at(".starbar-meta b").innerHTML.strip.imdb_unescape_html.split('/').first.to_f rescue nil
+      document.at(".starbar-meta b").content.split('/').first.strip.to_f rescue nil
     end
 
     # Returns an int containing the number of user ratings
     def votes
-      document.at("#tn15rating .tn15more").innerHTML.strip.imdb_unescape_html.gsub(/[^\d+]/, "").to_i rescue nil
+      document.at("#tn15rating .tn15more").content.strip.gsub(/[^\d+]/, "").to_i rescue nil
     end
 
     # Returns a string containing the tagline
     def tagline
-      document.search("h5[text()='Tagline:'] ~ div").first.innerHTML.gsub(/<.+>.+<\/.+>/, '').strip.imdb_unescape_html rescue nil
+      document.search("h5[text()='Tagline:'] ~ div").first.inner_html.gsub(/<.+>.+<\/.+>/, '').strip.imdb_unescape_html rescue nil
     end
 
     # Returns a string containing the mpaa rating and reason for rating
     def mpaa_rating
-      document.search("h5[text()='MPAA:'] ~ div").first.innerHTML.strip.imdb_unescape_html rescue nil
+      document.at("//a[starts-with(.,'MPAA')]/../following-sibling::*").content.strip rescue nil
     end
 
     # Returns a string containing the title
@@ -130,25 +130,34 @@ module Imdb
       if @title && !force_refresh
         @title
       else
-        @title = document.at("h1").innerHTML.split('<span').first.strip.imdb_unescape_html rescue nil
+        @title = document.at("h1").inner_html.split('<span').first.strip.imdb_unescape_html rescue nil
       end
     end
 
     # Returns an integer containing the year (CCYY) the movie was released in.
     def year
-      document.search('a[@href^="/year/"]').innerHTML.to_i
+      document.at("a[@href^='/year/']").content.to_i rescue nil
     end
 
     # Returns release date for the movie.
     def release_date
-      sanitize_release_date(document.search('h5[text()*=Release Date]').first.next_sibling.innerHTML.to_s) rescue nil
+      sanitize_release_date(document.at("h5[text()*='Release Date'] ~ div").content) rescue nil
+    end
+
+    # Returns filming locations from imdb_url/locations
+    def filming_locations
+      locations_document.search("#filming_locations_content .soda dt a").map { |link| link.content.strip } rescue []
     end
 
     private
 
-    # Returns a new Hpricot document for parsing.
+    # Returns a new Nokogiri document for parsing.
     def document
-      @document ||= Hpricot(Imdb::Movie.find_by_id(@id))
+      @document ||= Nokogiri::HTML(Imdb::Movie.find_by_id(@id))
+    end
+
+    def locations_document
+      @locations_document ||= Nokogiri::HTML(Imdb::Movie.find_by_id(@id, "locations"))
     end
 
     # Use HTTParty to fetch the raw HTML for this movie.
@@ -166,26 +175,17 @@ module Imdb
     end
 
     def sanitize_plot(the_plot)
-      the_plot = the_plot.imdb_strip_tags
-
       the_plot = the_plot.gsub(/add\ssummary|full\ssummary/i, "")
       the_plot = the_plot.gsub(/add\ssynopsis|full\ssynopsis/i, "")
-      the_plot = the_plot.gsub(/&nbsp;|&raquo;/i, "")
-      the_plot = the_plot.gsub(/see|more/i, "")
+      the_plot = the_plot.gsub(/see|more|\u00BB|\u00A0/i, "")
       the_plot = the_plot.gsub(/\|/i, "")
-
-      the_plot = the_plot.strip.imdb_unescape_html
+      the_plot.strip
     end
 
     def sanitize_release_date(the_release_date)
-      the_release_date = the_release_date.gsub(/<a.*a>/,"")
-      the_release_date = the_release_date.gsub(/&nbsp;|&raquo;/i, "")
-      the_release_date = the_release_date.gsub(/see|more/i, "")
-
-      the_release_date = the_release_date.strip.imdb_unescape_html
+      the_release_date.gsub(/see|more|\u00BB|\u00A0/i, "").strip
     end
 
   end # Movie
 
 end # Imdb
-

data/lib/imdb/episode.rb

@@ -11,13 +11,13 @@ module Imdb
 
     # Return the original air date for this episode
     def air_date
-      document.search('h5[text()*=Original Air Date]').first.next_sibling.innerHTML.to_s.strip.split("\n").first.strip rescue nil
+      document.at("h5[text()*='Original Air Date'] ~ div").content.strip.split("\n").first.strip rescue nil
     end
 
     private
 
     def document
-      @document ||= Hpricot(open(@url))
+      @document ||= Nokogiri::HTML(open(@url))
     end
   end
 end

data/lib/imdb/movie_list.rb

@@ -7,19 +7,15 @@ module Imdb
 
     private
     def parse_movies
-      document.search('a[@href^="/title/tt"]').reject do |element|
-        element.innerHTML.imdb_strip_tags.empty? ||
-        element.parent.innerHTML =~ /media from/i
+      document.search("a[@href^='/title/tt']").reject do |element|
+        element.inner_html.imdb_strip_tags.empty? ||
+        element.inner_html.imdb_strip_tags == "X" ||
+        element.parent.inner_html =~ /media from/i
       end.map do |element|
         id = element['href'][/\d+/]
 
-        data = element.parent.innerHTML.split("<br />")
-        if !data[0].nil? && !data[1].nil? && data[0] =~ /img/
-          title = data[1]
-        else
-          title = data[0]
-        end
-
+        data = element.parent.inner_html.split("<br />")
+        title = (!data[0].nil? && !data[1].nil? && data[0] =~ /img/) ? data[1] : data[0]
         title = title.imdb_strip_tags.imdb_unescape_html
         title.gsub!(/\s+\(\d\d\d\d\)$/, '')
 

data/lib/imdb/search.rb

@@ -23,7 +23,7 @@ module Imdb
 
     private
     def document
-      @document ||= Hpricot(Imdb::Search.query(@query))
+      @document ||= Nokogiri::HTML(Imdb::Search.query(@query))
     end
 
     def self.query(query)
@@ -31,15 +31,15 @@ module Imdb
     end
 
     def parse_movie
-      id                 = document.at("head/link[@rel='canonical']")['href'][/\d+/]
-      title              = document.at("h1").innerHTML.split('<span').first.strip.imdb_unescape_html
+      id    = document.at("head/link[@rel='canonical']")['href'][/\d+/]
+      title = document.at("h1").inner_html.split('<span').first.strip.imdb_unescape_html
 
       [Imdb::Movie.new(id, title)]
     end
 
     # Returns true if the search yielded only one result, an exact match
     def exact_match?
-      !document.at("//table[@id='title-overview-widget-layout']").nil?
+      !document.at("table[@id='title-overview-widget-layout']").nil?
     end
 
   end # Search

data/lib/imdb/season.rb

@@ -15,12 +15,12 @@ module Imdb
     def episodes
       @episodes = []
 
-      document.search("div.eplist a[@itemprop*=name]").each_with_index do |link, index|
+      document.search("div.eplist a[@itemprop*='name']").each_with_index do |link, index|
         @episodes << Imdb::Episode.new(
           link[:href].scan(/\d+/).first,
           @season_number,
           index + 1,
-          link.innerHTML.strip.imdb_unescape_html
+          link.content.strip
         )
       end
 
@@ -30,7 +30,7 @@ module Imdb
     private
 
     def document
-      @document ||= Hpricot(open(@url))
+      @document ||= Nokogiri::HTML(open(@url))
     end
   end
 end