PageRankr 1.6.0 → 1.7.0

data/CHANGELOG.md

@@ -1,5 +1,8 @@
 # Change Log
-## Version 1.6
+## Version 1.7.0
+* Merged in additions from iteration labs to add compete rank tracker and domain indexes.
+
+## Version 1.6.0
 
 * Added ability to get global alexa rank instead of just us alexa rank.
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    PageRankr (1.6.0)
+    PageRankr (1.7.0)
       json (>= 1.4.6)
       nokogiri (>= 1.4.1)
 
@@ -13,8 +13,8 @@ GEM
       rspec (~> 2.0)
       rspec-instafail (~> 0.1.4)
       ruby-progressbar (~> 0.0.9)
-    json (1.4.6)
-    nokogiri (1.4.3.1)
+    json (1.5.1)
+    nokogiri (1.4.4)
     rspec (2.1.0)
       rspec-core (~> 2.1.0)
       rspec-expectations (~> 2.1.0)
@@ -33,6 +33,4 @@ DEPENDENCIES
   PageRankr!
   bundler (>= 1.0.0)
   fuubar (>= 0.0.1)
-  json (>= 1.4.6)
-  nokogiri (>= 1.4.1)
   rspec (~> 2.1.0)

data/README.md

@@ -37,6 +37,28 @@ Valid search engines are: `:google, :bing, :yahoo, :altavista, :alltheweb, :alex
 
     PageRankr.backlink_trackers #=> [:alexa, :alltheweb, :altavista, :bing, :google, :yahoo]
 
+### Indexes
+
+Indexes are the result of doing a search with a query like "site:www.google.com". The number of returned results indicates how many pages of a domain are indexed by a particular search engine.
+
+    PageRankr.indexes('www.google.com', :google)       #=> {:google=>4860000}
+    PageRankr.indexes('www.google.com', :bing)         #=> {:bing=>2120000}
+
+If you don't specify a search engine, then all of them are used.
+
+    # this
+    PageRankr.indexes('www.google.com')
+        #=> {:bing=>2120000, :google=>4860000}
+
+    # is equivalent to
+    PageRankr.indexes('www.google.com', :google, :bing)
+        #=> {:bing=>2120000, :google=>4860000}
+
+You can also use the alias `index` instead of `indexes`.
+Valid search engines are: `:google, :bing`. To get this list you can do:
+
+    PageRankr.index_trackers #=> [:alexa, :alltheweb, :altavista, :bing, :google, :yahoo]
+
 ### Ranks
 
     PageRankr.ranks('www.google.com', :alexa, :google) #=> {:alexa=>{:us=>1, :global=>1}, :google=>10}
@@ -57,7 +79,7 @@ Google page ranks are in the range 0-10 where 10 is the most popular. If a site
 If you ever find something is broken it should now be much easier to fix it with version >= 1.3.0. For example, if the xpath used to lookup a backlink is broken, just override the method for that class to provide the correct xpath.
 
     module PageRankr
-      class Backlinks
+      class Backlinks < Tracker
         class Google < Backlink
           def xpath
             "my new awesome xpath"
@@ -71,7 +93,7 @@ If you ever find something is broken it should now be much easier to fix it with
 If you ever come across a site that provides a rank or backlinks you can hook that class up to automatically be use with PageRankr.
 
     module PageRankr
-      class Backlinks
+      class Backlinks < Tracker
         class Foo < Backlink
           def url(site)
             "http://example.com/?q=#{site}"
@@ -105,9 +127,7 @@ Then, just make sure you require the class and PageRankr and whenever you call P
 * Use API's where possible
 * Use [Typhoeus](https://github.com/pauldix/typhoeus) to improve speed when requesting multiple ranks and/or backlinks
 * Configuration
-    * API keys
-    * Alexa rank options
-* Add compete rank tracker
+    * Optionally use API keys
 
 ## Contributors
 * [Druwerd](http://github.com/Druwerd) - Use Google Search API instead of scraping.

data/Rakefile

@@ -2,4 +2,4 @@ require 'bundler'
 Bundler::GemHelper.install_tasks
 
 require 'rspec/core/rake_task'
-RSpec::Core::RakeTask.new(:spec)
+RSpec::Core::RakeTask.new(:spec)

data/lib/page_rankr.rb

@@ -1,6 +1,7 @@
 require File.join(File.dirname(__FILE__), "page_rankr", "tracker")
 require File.join(File.dirname(__FILE__), "page_rankr", "backlinks")
 require File.join(File.dirname(__FILE__), "page_rankr", "ranks")
+require File.join(File.dirname(__FILE__), "page_rankr", "indexes")
 
 module PageRankr
   class << self
@@ -14,6 +15,11 @@ module PageRankr
     end
     alias_method :rank, :ranks
     
+    def indexes(site, *index_trackers)
+      Indexes.new.lookup site, *index_trackers
+    end
+    alias_method :index, :indexes
+    
     def rank_trackers
       Ranks.new.rank_trackers
     end
@@ -21,5 +27,9 @@ module PageRankr
     def backlink_trackers
       Backlinks.new.backlink_trackers
     end
+    
+    def index_trackers
+      Indexes.new.index_trackers
+    end
   end
 end

data/lib/page_rankr/backlink.rb

@@ -1,3 +1,4 @@
+require 'rubygems'
 require 'nokogiri'
 require 'open-uri'
 

data/lib/page_rankr/index.rb

@@ -0,0 +1,17 @@
+require 'nokogiri'
+require 'open-uri'
+
+module PageRankr
+  class Index
+    attr_reader :indexes
+    alias_method :tracked, :indexes
+    
+    def initialize(site)
+      @indexes = clean Nokogiri::HTML(open url(site)).at(xpath).to_s
+    end
+    
+    def clean(backlink_count)
+      backlink_count.gsub(/[a-zA-Z,\s\(\)]/, '').to_i
+    end
+  end
+end

data/lib/page_rankr/indexes.rb

@@ -0,0 +1,9 @@
+require File.join(File.dirname(__FILE__), "index")
+require File.join(File.dirname(__FILE__), "indexes", "bing")
+require File.join(File.dirname(__FILE__), "indexes", "google")
+
+module PageRankr
+  class Indexes < Tracker
+    alias_method :index_trackers, :site_trackers
+  end
+end

data/lib/page_rankr/indexes/bing.rb

@@ -0,0 +1,19 @@
+require 'cgi'
+
+module PageRankr
+  class Indexes < Tracker
+    class Bing < Index
+      def url(site)
+        "http://www.bing.com/search?q=site%3A#{CGI.escape(site)}"
+      end
+      
+      def xpath
+        "//span[@class='sb_count']/text()"
+      end
+      
+      def clean(backlink_count)
+        super(backlink_count.gsub('1-10', ''))
+      end
+    end
+  end
+end

data/lib/page_rankr/indexes/google.rb

@@ -0,0 +1,19 @@
+require 'cgi'
+require 'json'
+
+module PageRankr
+  class Indexes < Tracker
+    class Google < Index
+      
+      # overloaded to use Google's AJAX search API
+      # http://code.google.com/apis/ajaxsearch/documentation/
+      def initialize(site)
+        @indexes = clean JSON.parse( open( url(site)).read )["responseData"]["cursor"]["estimatedResultCount"].to_s
+      end
+      
+      def url(site)
+        "http://ajax.googleapis.com/ajax/services/search/web?v=1.0&rsz=1&q=site%3A#{CGI.escape(site)}"
+      end
+    end
+  end
+end

data/lib/page_rankr/ranks.rb

@@ -1,6 +1,7 @@
 require File.join(File.dirname(__FILE__), "rank")
 require File.join(File.dirname(__FILE__), "ranks", "alexa")
 require File.join(File.dirname(__FILE__), "ranks", "google")
+require File.join(File.dirname(__FILE__), "ranks", "compete")
 
 module PageRankr
   class Ranks < Tracker

data/lib/page_rankr/ranks/compete.rb

@@ -0,0 +1,21 @@
+require 'open-uri'
+require 'cgi'
+require 'nokogiri'
+
+module PageRankr
+  class Ranks < Tracker
+    class Compete < Rank
+      def initialize(site)
+        @rank = Nokogiri::HTML(open(url(site))).search(xpath).to_s.gsub(',', '').to_i
+      end
+      
+      def xpath
+        "//div[@id='rank']/div[@class='number value']/text()"
+      end
+      
+      def url(site)
+        "http://siteanalytics.compete.com/#{CGI.escape(site)}/"
+      end
+    end
+  end
+end

data/lib/page_rankr/tracker.rb

@@ -14,7 +14,7 @@ module PageRankr
         name, klass = tracker.to_s.capitalize, self.class
         
         next unless klass.const_defined? name
-        
+
         tracked[tracker] = klass.const_get(name).new(site).tracked
       end
       tracked

data/lib/page_rankr/version.rb

@@ -1,3 +1,3 @@
 module PageRankr
-  VERSION = "1.6.0"
+  VERSION = "1.7.0"
 end

data/spec/page_rankr_spec.rb

@@ -88,4 +88,31 @@ describe PageRankr do
       end
     end
   end
+  
+  describe "#index_trackers" do
+    subject{ PageRankr.index_trackers }
+    
+    it{ should include(:google) }
+    it{ should include(:bing) }
+  end
+  
+  describe "#indexes" do
+    describe "success" do
+      subject{ PageRankr.indexes("google.com") }
+      
+      PageRankr.index_trackers.each do |tracker|
+        it{ should have_key(tracker) }
+        it{ subject[tracker].should >= 0 }
+      end
+    end
+    
+    describe "failure" do
+      subject{ PageRankr.indexes("please-dont-register-a-site-that-breaks-this-test.com") }
+      
+      PageRankr.index_trackers.each do |tracker|
+        it{ should have_key(tracker) }
+        it{ subject[tracker].should == 0 }
+      end
+    end
+  end
 end

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 1
-  - 6
+  - 7
   - 0
-  version: 1.6.0
+  version: 1.7.0
 platform: ruby
 authors: 
 - Allen Madsen
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-04 00:00:00 -05:00
+date: 2011-02-01 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -120,9 +120,14 @@ files:
 - lib/page_rankr/backlinks/bing.rb
 - lib/page_rankr/backlinks/google.rb
 - lib/page_rankr/backlinks/yahoo.rb
+- lib/page_rankr/index.rb
+- lib/page_rankr/indexes.rb
+- lib/page_rankr/indexes/bing.rb
+- lib/page_rankr/indexes/google.rb
 - lib/page_rankr/rank.rb
 - lib/page_rankr/ranks.rb
 - lib/page_rankr/ranks/alexa.rb
+- lib/page_rankr/ranks/compete.rb
 - lib/page_rankr/ranks/google.rb
 - lib/page_rankr/ranks/google/checksum.rb
 - lib/page_rankr/tracker.rb