spk-anemone 0.3.0 → 0.3.1

data/CHANGELOG.rdoc

@@ -1,3 +1,13 @@
+== 0.3.1 / 2010-01-22
+
+* Minor enhancements
+
+  * Added an attr_accessor to Page for the HTTP response body
+
+* Bug fixes
+
+  * Fixed incorrect method calls in CLI scripts
+
 == 0.3.0 / 2009-12-15
 
 * Major enchancements

data/lib/anemone/cli/count.rb

@@ -7,7 +7,7 @@ rescue
   puts <<-INFO
 Usage:
   anemone count <url>
-  
+
 Synopsis:
   Crawls a site starting at the given URL and outputs the total number
   of unique pages on the site.
@@ -17,6 +17,6 @@ end
 
 Anemone.crawl(url) do |anemone|
   anemone.after_crawl do |pages|
-    puts pages.uniq.size
+    puts pages.uniq!.size
   end
 end

data/lib/anemone/cli/pagedepth.rb

@@ -17,16 +17,16 @@ end
 
 Anemone.crawl(root) do |anemone|
   anemone.skip_links_like %r{^/c/$}, %r{^/stores/$}
-  
+
   anemone.after_crawl do |pages|
-    pages = pages.shortest_paths!(root).uniq
-    
+    pages = pages.shortest_paths!(root).uniq!
+
     depths = pages.values.inject({}) do |depths, page|
       depths[page.depth] ||= 0
       depths[page.depth] += 1
       depths
     end
-    
+
     depths.sort.each { |depth, count| puts "Depth: #{depth} Count: #{count}" }
   end
 end

data/lib/anemone/core.rb

@@ -7,7 +7,7 @@ require 'anemone/storage'
 
 module Anemone
 
-  VERSION = '0.3.0';
+  VERSION = '0.3.1';
 
   #
   # Convenience method to start a crawl
@@ -193,7 +193,7 @@ module Anemone
       @robots = Robots.new(@opts[:user_agent]) if @opts[:obey_robots_txt]
     end
 
-    # Generate Authorization string only if not already set
+    # Generate Authorization string and set authorization opts
     def authorization(auth=nil)
       require 'base64'
       if auth.is_a?(String) && auth.include?(':')

data/lib/anemone/page.rb

@@ -6,6 +6,8 @@ module Anemone
 
     # The URL of the page
     attr_reader :url
+    # The raw HTTP response body of the page
+    attr_reader :body
     # Headers of the HTTP response
     attr_reader :headers
     # URL of the page this one redirected to, if any
@@ -50,7 +52,9 @@ module Anemone
       @fetched = !params[:code].nil?
     end
 
+    #
     # Array of distinct A tag HREFs from the page
+    #
     def links
       return @links unless @links.nil?
       @links = []
@@ -66,18 +70,26 @@ module Anemone
       @links
     end
 
+    #
     # Nokogiri document for the HTML body
+    #
     def doc
       return @doc if @doc
       @doc = Nokogiri::HTML(@body) if @body && html? rescue nil
     end
 
+    #
     # Delete the Nokogiri document and response body to conserve memory
+    #
     def discard_doc!
       links # force parsing of page links before we trash the document
       @doc = @body = nil
     end
 
+    #
+    # Was the page successfully fetched?
+    # +true+ if the page was fetched with no error, +false+ otherwise.
+    #
     def fetched?
       @fetched
     end

data/spec/page_spec.rb

@@ -17,6 +17,12 @@ module Anemone
       fail_page.fetched?.should == false
     end
 
+    it "should store and expose the response body of the HTTP request" do
+      body = 'test'
+      page = @http.fetch_page(FakePage.new('body_test', {:body => body}).url)
+      page.body.should == body
+    end
+
     it "should record any error that occurs during fetch_page" do
       @page.should respond_to(:error)
       @page.error.should be_nil

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: spk-anemone
 version: !ruby/object:Gem::Version 
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors: 
 - Chris Kite
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-03 00:00:00 +01:00
+date: 2010-01-29 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency