simplecrawler 0.1.3 → 0.1.4

data/lib/simplecrawler.rb

@@ -23,7 +23,7 @@ module SimpleCrawler
 	require File.dirname(__FILE__) + '/document'
 
 	MARKUP_MIME_TYPES = ["text/html", "text/xml", "application/xml", "application/xhtml+xml"]
-	VERSION = "0.1.3"
+	VERSION = "0.1.4"
 
 	class Crawler
 
@@ -103,7 +103,7 @@ module SimpleCrawler
 			doc = Document.new
 			begin
 				uri = @site_uri.clone
-				uri.path = uri.path + path if path != "/"
+				uri.path = path if path != "/"
 				doc.uri = uri
 
 				log("Trying #{uri}")

data/tests/simplecrawler_test.rb

@@ -12,8 +12,14 @@ class SimpleCrawlerTest < Test::Unit::TestCase
   def test_initialize_crawler
 	  @crawler = SimpleCrawler::Crawler.new("http://www.example.com/")
 	  assert @crawler.queue.length == 1
+	  assert_equal "/", @crawler.queue[0]
   end
 
+  def test_initialize_crawler_with_path
+	  @crawler = SimpleCrawler::Crawler.new("http://www.example.com/deep/down/in/hierarchy/")
+	  assert @crawler.queue.length == 1
+	  assert_equal "/deep/down/in/hierarchy/", @crawler.queue[0]
+  end
 
   def test_initialize_crawler_without_uri_path
 	  @crawler = SimpleCrawler::Crawler.new("http://www.example.com")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: simplecrawler
 version: !ruby/object:Gem::Version 
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors: 
 - Peter Krantz
@@ -9,7 +9,7 @@ autorequire: simplecrawler
 bindir: bin
 cert_chain: []
 
-date: 2008-01-26 00:00:00 +01:00
+date: 2008-09-17 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency