wombat 0.3.0 → 0.3.1

data/README.md

@@ -1,6 +1,6 @@
 # Wombat
 
-[![CI Build Status](https://secure.travis-ci.org/felipecsl/wombat.png?branch=master)](travis) [![Dependency Status](https://gemnasium.com/felipecsl/wombat.png?travis)](gemnasium)
+[![CI Build Status](https://secure.travis-ci.org/felipecsl/wombat.png?branch=master)][travis] [![Dependency Status](https://gemnasium.com/felipecsl/wombat.png?travis)][gemnasium]
 
 [travis]: http://travis-ci.org/felipecsl/wombat
 [gemnasium]: https://gemnasium.com/felipecsl/wombat
@@ -85,6 +85,13 @@ my_crawler.crawl
 
  * Felipe Lima ([@felipecsl](https://github.com/felipecsl))
  * [@sigi](https://github.com/sigi)
+ * Daniel Naves de Carvalho ([@danielnc](https://github.com/danielnc))
+
+## Changelog
+
+### version 0.3.1
+
+ * Added the ability to provide a block to Crawler#crawl and override the default crawler properties for a one off run (thanks to @danielnc)
 
 ## Copyright
 

data/VERSION

@@ -1 +1 @@
-0.3.0
+0.3.1

data/lib/wombat/crawler.rb

@@ -10,8 +10,19 @@ module Wombat
     include Parser
     extend ActiveSupport::Concern
 
-    def crawl
-      parse self.class.send(:metadata)
+    def crawl(&block)
+      if block
+        @metadata_dup = self.class.send(:metadata).clone
+        instance_eval do
+          def method_missing method, *args, &block
+            @metadata_dup.send method, *args, &block
+          end
+        end
+        self.instance_eval &block
+        parse @metadata_dup
+      else
+        parse self.class.send(:metadata)
+      end
     end
 
     module ClassMethods

data/lib/wombat/node_selector.rb

@@ -4,7 +4,7 @@ module Wombat
       return [selector.to_s] if selector.is_a? Symbol
       return context.xpath selector[6..-1], namespaces if selector.start_with? "xpath="
       return context.css selector[4..-1] if selector.start_with? "css="
-      nil
+      selector
     end
   end
 end

data/spec/crawler_spec.rb

@@ -9,16 +9,16 @@ describe Wombat::Crawler do
 
   it 'should call the provided block' do
     event_called = false
-    
+
     @crawler.event { event_called = true }
-    
+
     event_called.should be_true
   end
 
   it 'should provide metadata to yielded block' do
     @crawler.event do |e|
       e.should_not be_nil
-    end 
+    end
   end
 
   it 'should store assigned metadata information' do
@@ -38,7 +38,7 @@ describe Wombat::Crawler do
       arg["venue"]["name"].selector.should == "Scooba"
       arg["location"]["latitude"].selector.should == -50.2323
     end
-    
+
     @crawler_instance.crawl
   end
 
@@ -57,8 +57,8 @@ describe Wombat::Crawler do
   end
 
   it 'should be able to assign arbitrary plain text metadata' do
-    @crawler.some_data("/event/list", :html, "geo") {|p| true }
-    
+    @crawler.some_data("/event/list", :html, "geo") { |p| true }
+
     @crawler_instance.should_receive(:parse) do |arg|
       prop = arg['some_data']
       prop.name.should == "some_data"
@@ -67,7 +67,7 @@ describe Wombat::Crawler do
       prop.namespaces.should == "geo"
       prop.callback.should_not be_nil
     end
-    
+
     @crawler_instance.crawl
   end
 
@@ -107,16 +107,39 @@ describe Wombat::Crawler do
       it["title"].selector.should == "css=.title"
       it["body"].selector.should == "css=.body"
       it["event"]["all"].selector.should == "yeah"
-    end 
+    end
 
     @crawler_instance.crawl
   end
 
-  it 'should assign metadata forma' do
+  it 'should assign metadata format' do
     @crawler_instance.should_receive(:parse) do |arg|
       arg[:format].should == :xml
     end
     @crawler.format :xml
     @crawler_instance.crawl
   end
+
+  it 'should crawl with block' do
+    @crawler.base_url "danielnc.com"
+    @crawler.list_page "/itens"
+
+    @crawler_instance.should_receive(:parse) do |arg|
+      arg[:base_url].should == "danielnc.com"
+      arg[:list_page].should == "/itens/1"
+    end
+
+    @crawler_instance.crawl do
+      list_page "/itens/1"
+    end
+
+    another_instance = @crawler.new
+
+    another_instance.should_receive(:parse) do |arg|
+      arg[:base_url].should == "danielnc.com"
+      arg[:list_page].should == "/itens"
+    end
+
+    another_instance.crawl
+  end
 end

data/wombat.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "wombat"
-  s.version = "0.3.0"
+  s.version = "0.3.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Felipe Lima"]
-  s.date = "2012-03-25"
+  s.date = "2012-04-12"
   s.description = "Generic Web crawler with a DSL that parses structured data from web pages"
   s.email = "felipe.lima@gmail.com"
   s.extra_rdoc_files = [

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: wombat
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-25 00:00:00.000000000 Z
+date: 2012-04-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize