gscraper 0.2.3 → 0.2.4

data/History.txt

@@ -1,3 +1,10 @@
+=== 0.2.4 / 2009-03-18
+
+* Added SponsoredAd#direct_link.
+* Fixed a bug in SponsoredAd#direct_url where direct links we're not
+  being URI escaped.
+* Removed last references to Hpricot, replacing them with Nokogiri.
+
 === 0.2.3 / 2009-01-27
 
 * Fixed a bug in GScraper::Search::WebQuery#page, when the search query

data/README.txt

@@ -1,6 +1,7 @@
 = GScraper
 
 * http://gscraper.rubyforge.org/
+* http://github.com/postmodern/gscraper/
 * Postmodern (postmodern.mod3 at gmail.com)
 
 == DESCRIPTION:
@@ -127,7 +128,7 @@ GScraper is a web-scraping interface to various Google Services.
 
 GScraper - A web-scraping interface to various Google Services.
 
-Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 
 This program is free software; you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

data/lib/gscraper.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/extensions.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/extensions/uri.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/extensions/uri/http.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/gscraper.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -22,6 +22,7 @@
 
 require 'uri/http'
 require 'mechanize'
+require 'nokogiri'
 require 'open-uri'
 
 module GScraper
@@ -127,10 +128,10 @@ module GScraper
   end
 
   #
-  # Similar to GScraper.open_uri but returns an Hpricot document.
+  # Similar to GScraper.open_uri but returns a Nokogiri::HTML document.
   #
   def GScraper.open_page(uri,options={})
-    Hpricot(GScraper.open_uri(uri,options))
+    Nokogiri::HTML(GScraper.open_uri(uri,options))
   end
 
   #

data/lib/gscraper/has_pages.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/licenses.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/page.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/search.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/search/ajax_query.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -28,6 +28,7 @@ require 'gscraper/has_pages'
 require 'gscraper/gscraper'
 
 require 'json'
+require 'nokogiri'
 
 module GScraper
   module Search
@@ -160,9 +161,9 @@ module GScraper
           if (hash.kind_of?(Hash) && hash['results'])
             hash['results'].each_with_index do |result,index|
               rank = rank_offset + (index + 1)
-              title = Hpricot(result['title']).inner_text
+              title = Nokogiri::HTML(result['title']).inner_text
               url = URI(result['unescapedUrl'])
-              summary = Hpricot(result['content']).inner_text
+              summary = Nokogiri::HTML(result['content']).inner_text
               cached_url = URI(result['cacheUrl'])
 
               new_page << Result.new(rank,title,url,summary,cached_url)

data/lib/gscraper/search/page.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/search/query.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -29,8 +29,6 @@ require 'gscraper/has_pages'
 require 'gscraper/licenses'
 require 'gscraper/gscraper'
 
-require 'hpricot'
-
 module GScraper
   module Search
     class Query

data/lib/gscraper/search/result.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/search/search.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/search/web_query.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -349,7 +349,7 @@ module GScraper
             result = results[index]
 
             rank = rank_offset + (index + 1)
-            link = result.at('a.l')
+            link = result.at('h3.r/a')
             title = link.inner_text
             url = URI(link.get_attribute('href'))
             summary_text = ''

data/lib/gscraper/sponsored_ad.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -39,11 +39,18 @@ module GScraper
       @url = url
     end
 
+    #
+    # Returns the direct link of the ad.
+    #
+    def direct_link
+      @url.query_params['adurl'] || @url.query_params['q']
+    end
+
     #
     # Returns the direct URL of the ad.
     #
     def direct_url
-      URI(@url.query_params['adurl'] || @url.query_params['q'])
+      URI(URI.escape(direct_link))
     end
 
     #

data/lib/gscraper/sponsored_links.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

data/lib/gscraper/version.rb

@@ -2,7 +2,7 @@
 #--
 # GScraper - A web-scraping interface to various Google Services.
 #
-# Copyright (c) 2007-2008 Hal Brodigan (postmodern.mod3 at gmail.com)
+# Copyright (c) 2007-2009 Hal Brodigan (postmodern.mod3 at gmail.com)
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -21,5 +21,5 @@
 #
 
 module GScraper
-  VERSION = '0.2.3'
+  VERSION = '0.2.4'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: gscraper
 version: !ruby/object:Gem::Version 
-  version: 0.2.3
+  version: 0.2.4
 platform: ruby
 authors: 
 - Postmodern
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-01-27 00:00:00 -08:00
+date: 2009-03-18 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -30,7 +30,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 1.8.3
+        version: 1.10.0
     version: 
 description: GScraper is a web-scraping interface to various Google Services.
 email: