apollo-crawler 0.0.47 → 0.0.48

data/lib/apollo_crawler/crawler.rb

@@ -25,7 +25,7 @@ module Apollo
 			# - (3) Go to (0) eventually
 			def etl(url=nil)
 				# Look for passed URL use default instead and fail if it is not valid
-				if(url.empty?)
+				if(url.nil? || url.empty?)
 					url = self.url
 				end
 
@@ -81,7 +81,7 @@ module Apollo
 					return nil
 				end
 
-				raw = open(self.url).read
+				raw = open(url).read
 
 				# TODO: Encapsulate and make more robust => invalid hostname, timeouts and so
 				doc = Nokogiri::HTML(raw)

data/lib/apollo_crawler/crawlers/google_com/google.rb

@@ -0,0 +1,26 @@
+require File.join(File.dirname(__FILE__), '..', '..', 'crawler') 
+
+module Apollo
+	module Crawlers
+		class Google < Crawler
+			@@MATCHER_ITEM = "//h3/a"
+
+			def name()
+				return "Google"
+			end
+
+			def url()
+				return "http://www.google.com/search?q=ruby"
+			end
+
+			def extract_data(doc)
+				res = doc.xpath(@@MATCHER_ITEM).map { |i|
+					{ 
+						:text => i.text,
+						:link => URI.join(self.url, i['href'])
+					}
+				}
+			end
+		end
+	end # Crawlers
+end # Apollo

data/lib/apollo_crawler/version.rb

@@ -1,5 +1,5 @@
 module Apollo
 	module Crawler
-		VERSION = '0.0.47'
+		VERSION = '0.0.48'
 	end # Crawler
 end # Apollo

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: apollo-crawler
 version: !ruby/object:Gem::Version
-  version: 0.0.47
+  version: 0.0.48
   prerelease: 
 platform: ruby
 authors:
@@ -234,6 +234,7 @@ files:
 - ./lib/apollo_crawler/crawler.rb
 - ./lib/apollo_crawler/crawlers/stackoverflow_com/stackoverflow.rb
 - ./lib/apollo_crawler/crawlers/xkcd_com/xkcd.rb
+- ./lib/apollo_crawler/crawlers/google_com/google.rb
 - ./lib/apollo_crawler/crawlers/slashdot_org/slashdot.rb
 - ./lib/apollo_crawler/crawlers/firmy_cz/firmy.rb
 - ./lib/apollo_crawler/crawlers/alexa_com/alexa.rb
@@ -244,7 +245,6 @@ files:
 homepage: https://github.com/korczis/apollo-crawler
 licenses:
 - MIT
-- GPL-2
 post_install_message: Thanks for installing Apollo Crawler!
 rdoc_options: []
 require_paths: