wombat 2.3.0 → 2.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 29b144dfbf340e596997d9ff5e8bc0fc0c227bad
-  data.tar.gz: d412426f32c1791ee5340777f24b62ac084da162
+  metadata.gz: d495fd45c7c451739a77c6f9474b2eafd5b8324a
+  data.tar.gz: d665211fe3918cdf30b46c5baba237b6ba12d788
 SHA512:
-  metadata.gz: a13b6b58044e8ab05bf0ef35c3e25db69adae253423b57a70b26e2b38181c4291bb77dc67ed4bb28a16b6757145a4cf183b74a3a606387cc4c7217ccab21736b
-  data.tar.gz: 45ad1f8f8e9e026ea7935b1bd925efcd393f8b8993710ada64839db41e5a8b871831eb29d7473af1988379b8baf3bb01f2b677202443bb704a75e70fa8e05be0
+  metadata.gz: 7245007b0fddde801a764d1777a041a25e3453972edbc9bcf710876804bd5d4b23f24a5c2b477798ad4886f660b28591f230c544b1e5c3ee90a859bf855eafb9
+  data.tar.gz: 442634497971982fb0142540d6cd2ddc7b2224e1f78ed032eae448d72a2db8e73ac88d6841965c6d6d4c4350c2ea274bc2f6c377dfe0f9021ab238af159e0340

data/Gemfile.lock

@@ -1,31 +1,31 @@
 GEM
   remote: http://rubygems.org/
   specs:
-    activesupport (4.1.8)
-      i18n (~> 0.6, >= 0.6.9)
+    activesupport (4.2.0)
+      i18n (~> 0.7)
       json (~> 1.7, >= 1.7.7)
       minitest (~> 5.1)
-      thread_safe (~> 0.1)
+      thread_safe (~> 0.3, >= 0.3.4)
       tzinfo (~> 1.1)
-    addressable (2.3.6)
+    addressable (2.3.7)
     builder (3.2.2)
-    coveralls (0.7.2)
-      multi_json (~> 1.3)
-      rest-client (= 1.6.7)
-      simplecov (>= 0.7)
-      term-ansicolor (= 1.2.2)
-      thor (= 0.18.1)
+    coveralls (0.7.11)
+      multi_json (~> 1.10)
+      rest-client (>= 1.6.8, < 2)
+      simplecov (~> 0.9.1)
+      term-ansicolor (~> 1.3)
+      thor (~> 0.19.1)
     descendants_tracker (0.0.4)
       thread_safe (~> 0.3, >= 0.3.1)
     diff-lcs (1.2.5)
     docile (1.1.5)
-    domain_name (0.5.22)
+    domain_name (0.5.23)
       unf (>= 0.0.5, < 1.0.0)
     fakeweb (1.3.0)
-    faraday (0.9.0)
+    faraday (0.9.1)
       multipart-post (>= 1.2, < 3)
-    git (1.2.8)
-    github_api (0.12.2)
+    git (1.2.9.1)
+    github_api (0.12.3)
       addressable (~> 2.3)
       descendants_tracker (~> 0.0.4)
       faraday (~> 0.8, < 0.10)
@@ -33,11 +33,11 @@ GEM
       multi_json (>= 1.7.5, < 2.0)
       nokogiri (~> 1.6.3)
       oauth2
-    hashie (3.3.2)
-    highline (1.6.21)
+    hashie (3.4.0)
+    highline (1.7.1)
     http-cookie (1.0.2)
       domain_name (~> 0.5)
-    i18n (0.6.11)
+    i18n (0.7.0)
     jeweler (2.0.1)
       builder
       bundler (>= 1.0)
@@ -47,8 +47,8 @@ GEM
       nokogiri (>= 1.5.10)
       rake
       rdoc
-    json (1.8.1)
-    jwt (1.2.0)
+    json (1.8.2)
+    jwt (1.3.0)
     mechanize (2.7.3)
       domain_name (~> 0.5, >= 0.5.1)
       http-cookie (~> 1.0)
@@ -59,14 +59,15 @@ GEM
       ntlm-http (~> 0.1, >= 0.1.1)
       webrobots (>= 0.0.9, < 0.2)
     mime-types (2.4.3)
-    mini_portile (0.6.1)
-    minitest (5.4.3)
-    multi_json (1.10.1)
+    mini_portile (0.6.2)
+    minitest (5.5.1)
+    multi_json (1.11.0)
     multi_xml (0.5.5)
     multipart-post (2.0.0)
     net-http-digest_auth (1.4)
     net-http-persistent (2.9.4)
-    nokogiri (1.6.5)
+    netrc (0.10.3)
+    nokogiri (1.6.6.2)
       mini_portile (~> 0.6.0)
     ntlm-http (0.1.1)
     oauth2 (1.0.0)
@@ -75,34 +76,35 @@ GEM
       multi_json (~> 1.3)
       multi_xml (~> 0.5)
       rack (~> 1.2)
-    rack (1.5.2)
-    rake (10.4.0)
-    rdoc (4.1.2)
-      json (~> 1.4)
-    rest-client (1.6.7)
-      mime-types (>= 1.16)
-    rspec (3.1.0)
-      rspec-core (~> 3.1.0)
-      rspec-expectations (~> 3.1.0)
-      rspec-mocks (~> 3.1.0)
-    rspec-core (3.1.7)
-      rspec-support (~> 3.1.0)
-    rspec-expectations (3.1.2)
+    rack (1.6.0)
+    rake (10.4.2)
+    rdoc (4.2.0)
+    rest-client (1.7.3)
+      mime-types (>= 1.16, < 3.0)
+      netrc (~> 0.7)
+    rspec (3.2.0)
+      rspec-core (~> 3.2.0)
+      rspec-expectations (~> 3.2.0)
+      rspec-mocks (~> 3.2.0)
+    rspec-core (3.2.1)
+      rspec-support (~> 3.2.0)
+    rspec-expectations (3.2.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.2.0)
+    rspec-mocks (3.2.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.1.0)
-    rspec-mocks (3.1.3)
-      rspec-support (~> 3.1.0)
-    rspec-support (3.1.2)
-    simplecov (0.9.1)
+      rspec-support (~> 3.2.0)
+    rspec-support (3.2.2)
+    simplecov (0.9.2)
       docile (~> 1.1.0)
       multi_json (~> 1.0)
-      simplecov-html (~> 0.8.0)
-    simplecov-html (0.8.0)
-    term-ansicolor (1.2.2)
-      tins (~> 0.8)
-    thor (0.18.1)
+      simplecov-html (~> 0.9.0)
+    simplecov-html (0.9.0)
+    term-ansicolor (1.3.0)
+      tins (~> 1.0)
+    thor (0.19.1)
     thread_safe (0.3.4)
-    tins (0.13.2)
+    tins (1.3.5)
     tzinfo (1.2.2)
       thread_safe (~> 0.1)
     unf (0.1.4)

data/README.md

@@ -14,8 +14,6 @@ Web scraper with an elegant DSL that parses structured data from web pages.
 
 ``gem install wombat``
 
-Obs: Requires ruby 1.9.3 (activesupport requires Ruby version >= 1.9.3)
-
 ## Scraping a page:
 
 The simplest way to use Wombat is by calling ``Wombat.crawl`` and passing it a block:
@@ -48,18 +46,18 @@ end
 
 ```ruby
 {
-  "headline"=>"Build software better, together.", 
-  "subheading"=>"Powerful collaboration, code review, and code management for open source and private projects. Need private repositories? Upgraded plans start at $7/mo.", 
+  "headline"=>"Build software better, together.",
+  "subheading"=>"Powerful collaboration, code review, and code management for open source and private projects. Need private repositories? Upgraded plans start at $7/mo.",
   "what_is"=>[
-    "Great collaboration starts with communication.", 
-    "Friction-less development across teams.", 
-    "World's largest open source community.", 
+    "Great collaboration starts with communication.",
+    "Friction-less development across teams.",
+    "World's largest open source community.",
     "Do more with powerful integrations."
-  ], 
+  ],
   "links"=>{
-    "explore"=>"Love", 
-    "features"=>"Features", 
-    "enterprise"=>"Enterprise", 
+    "explore"=>"Love",
+    "features"=>"Features",
+    "enterprise"=>"Enterprise",
     "blog"=>"Blog"
   }
 }
@@ -89,4 +87,3 @@ end
 ## Copyright
 
 Copyright (c) 2012 Felipe Lima. See LICENSE.txt for further details.
-

data/VERSION

@@ -1 +1 @@
-2.3.0
+2.4.0

data/lib/wombat.rb

@@ -5,7 +5,7 @@ require 'wombat/crawler'
 module Wombat
 	class << self
 
-    attr_reader :proxy_args
+    attr_reader :proxy_args, :user_agent, :user_agent_alias
 
 		def crawl(&block)
 			klass = Class.new
@@ -21,6 +21,14 @@ module Wombat
       @proxy_args = args
     end
 
+    def set_user_agent(user_agent)
+      @user_agent = user_agent
+    end
+
+    def set_user_agent_alias(user_agent_alias)
+      @user_agent_alias = user_agent_alias
+    end
+
 		alias_method :scrape, :crawl
 	end
-end
+end

data/lib/wombat/processing/parser.rb

@@ -27,6 +27,8 @@ module Wombat
           }
         }
         @mechanize.set_proxy(*Wombat.proxy_args) if Wombat.proxy_args
+        @mechanize.user_agent = Wombat.user_agent if Wombat.user_agent
+        @mechanize.user_agent_alias = Wombat.user_agent_alias if Wombat.user_agent_alias
       end
 
       def parse(metadata)

data/spec/wombat_spec.rb

@@ -20,8 +20,12 @@ describe Wombat do
 	it 'should provide configuration method with block' do
 		Wombat.configure do |config|
 			config.set_proxy "10.0.0.1", 8080
+			config.set_user_agent "Wombat"
+			config.set_user_agent_alias 'Mac Safari'
 		end
 		Wombat.proxy_args.should == ["10.0.0.1", 8080]
+		Wombat.user_agent.should == 'Wombat'
+		Wombat.user_agent_alias.should == 'Mac Safari'
 	end
 
 	it 'should accept regular properties (non-selectors)' do
@@ -38,4 +42,4 @@ describe Wombat do
 			}.should_not raise_error
 		end
 	end
-end
+end

data/wombat.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: wombat 2.3.0 ruby lib
+# stub: wombat 2.4.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "wombat"
-  s.version = "2.3.0"
+  s.version = "2.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Felipe Lima"]
-  s.date = "2014-12-02"
+  s.date = "2015-03-05"
   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 = [
@@ -82,7 +82,7 @@ Gem::Specification.new do |s|
   s.homepage = "http://felipecsl.github.com/wombat"
   s.licenses = ["MIT"]
   s.required_ruby_version = Gem::Requirement.new(">= 1.9")
-  s.rubygems_version = "2.2.2"
+  s.rubygems_version = "2.4.6"
   s.summary = "Ruby DSL to scrape web pages"
 
   if s.respond_to? :specification_version then

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wombat
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.4.0
 platform: ruby
 authors:
 - Felipe Lima
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-12-02 00:00:00.000000000 Z
+date: 2015-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -251,7 +251,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.6
 signing_key: 
 specification_version: 4
 summary: Ruby DSL to scrape web pages