scrapie 0.1.0

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/Gemfile

@@ -0,0 +1,14 @@
+source "http://rubygems.org"
+
+gem "mechanize"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "sham_rack", ">= 0"
+  gem "sinatra" # For sham_rack magic!
+  gem "rspec", ">= 0"
+  gem "bundler", "~> 1.0.0"
+  gem "jeweler", "~> 1.6.4"
+  gem "rcov", ">= 0"
+end

data/Gemfile.lock

@@ -0,0 +1,51 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    diff-lcs (1.1.3)
+    git (1.2.5)
+    jeweler (1.6.4)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+    mechanize (2.0.1)
+      net-http-digest_auth (~> 1.1, >= 1.1.1)
+      net-http-persistent (~> 1.8)
+      nokogiri (~> 1.4)
+      webrobots (~> 0.0, >= 0.0.9)
+    net-http-digest_auth (1.1.1)
+    net-http-persistent (1.9)
+    nokogiri (1.5.0)
+    rack (1.3.5)
+    rack-protection (1.1.4)
+      rack
+    rake (0.9.2.2)
+    rcov (0.9.11)
+    rspec (2.7.0)
+      rspec-core (~> 2.7.0)
+      rspec-expectations (~> 2.7.0)
+      rspec-mocks (~> 2.7.0)
+    rspec-core (2.7.1)
+    rspec-expectations (2.7.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.7.0)
+    sham_rack (1.3.3)
+      rack
+    sinatra (1.3.1)
+      rack (~> 1.3, >= 1.3.4)
+      rack-protection (~> 1.1, >= 1.1.2)
+      tilt (~> 1.3, >= 1.3.3)
+    tilt (1.3.3)
+    webrobots (0.0.12)
+      nokogiri (>= 1.4.4)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.0.0)
+  jeweler (~> 1.6.4)
+  mechanize
+  rcov
+  rspec
+  sham_rack
+  sinatra

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2011 Adrian Pike
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,55 @@
+= scrapie
+
+Hey, it's Scrapie! It's 2011, we should be able to scrape sites for their juicy data in a delicious fashion instead of having to hack something together every time.
+
+It's basically a tool that allows you to really simply and quickly fab up a class that translates CSS selectors into attributes, and lets you specify your own translations on query params.
+
+== Example
+
+  class Airplane < Scrapie
+    url 'http://registry.faa.gov/aircraftinquiry/NNum_Results.aspx'
+    params {
+      :n_number => 'NNumbertxt'
+    }
+    attributes {
+      'serial_number' => 'div#serial_number',
+      'classname' => '.class_name'
+    }
+    before_fetch do |agent|
+      # Do stuff with my agent, like log in or hax the gibson
+    end
+    after_fetch do |agent|
+      # Do more neatu stuff with my agent
+    end
+  
+  
+    # Other posisbilities
+    method :get
+    agent_options { :options_to_send_to_my_new_mechanize_agent => 'BE COOL MAN' }
+  end
+
+  a = Airplane.find(:n_number => '12345') # => Fetches http://registry.faa.gov/aircraftinquiry/NNum_Results.aspx?NNumbertxt=12345
+  a.serial_number = 'a cool serial number'
+
+== Todo
+
+* Set up the callbacks
+* Sanitize
+* Refactor
+* Make it cooler!
+
+== Contributing to scrapie
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
+* Fork the project
+* Start a feature/bugfix branch
+* Commit and push until you are happy with your contribution
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2011 Adrian Pike. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,54 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "scrapie"
+  gem.homepage = "http://github.com/adrianpike/scrapie"
+  gem.license = "MIT"
+  gem.summary = %Q{Scrapie scrapes things for great justice.}
+  gem.description = %Q{Scrapie is a tool that allows you to really simply and quickly fab up a class that translates CSS selectors into attributes, and lets you specify your own translations on query params. }
+  gem.email = "adrian@pikeapps.com"
+  gem.authors = ["Adrian Pike"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+
+require 'rspec'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new('spec') do |t|
+  t.pattern = 'spec/*_spec.rb'
+#  t.rspec_opts = ["--backtrace"]
+end
+
+require 'rcov/rcovtask'
+Rcov::RcovTask.new do |test|
+  test.libs << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+  test.rcov_opts << '--exclude "gems/*"'
+end
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "scrapie #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/scrapie.rb

@@ -0,0 +1,55 @@
+require 'mechanize'
+
+class Scrapie
+  class ScrapieException < Exception; end
+  class NoAttributesException < ScrapieException; end
+  
+  def self.url(url)
+    @url = url
+  end
+  def self.params(params)
+    @params = params
+  end
+  def self.http_method(method)
+    @http_method = method
+  end
+  def self.attributes(attributes)
+    @attributes = attributes
+    attributes.each {|name,page_selector|
+      self.send(:attr_accessor, name)
+    }
+  end
+  
+  # find()
+  # find(:foo => bar)
+  # find(:foo => bar, :baz => bizzle)  
+  def self.find(opts = {})
+    raise NoAttributesException unless (@attributes and @attributes.size > 0)
+    a = Mechanize.new
+    
+    # Let's build out the parameters now
+    params = Hash[opts.collect{|k,v|
+      [@params[k], v] if @params and @params[k]
+    }]
+    
+    page = a.send(@http_method || :get, @url, params)
+    
+    new_object = self.new
+    @attributes.each {|name, page_selector|
+      new_object.send(name + '=', page.search(page_selector).inner_html)
+    }
+    
+    new_object
+  end
+  
+  # Callbacks # TODO
+  
+  def self.before_fetch
+    
+  end
+  
+  def self.after_fetch
+    
+  end
+  
+end

data/spec/helper.rb

@@ -0,0 +1,15 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rspec'
+require 'sham_rack'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'scrapie'

data/spec/scrapie_spec.rb

@@ -0,0 +1,98 @@
+require 'helper'
+
+ShamRack.at("scrapietest").sinatra do
+  get "/test1" do
+    "No attributes here chief"
+  end
+  get "/test_with_params" do
+    "<div id='param'>#{params[:test_param_for_getting]}</div><div id='param_upcased'>#{params[:test_param_for_getting].upcase}</div>"
+  end
+  get "/test" do
+    "<div class='foo'>example</div>"
+  end
+  get '/500' do
+    DERP
+  end
+  post '/post' do
+    "<div id='post_param'>#{params[:le_post]}</div>"
+  end
+end
+
+class NoAttributeScrapie < Scrapie
+  url 'http://scrapietest/test1'
+end
+
+class BasicScrapie < Scrapie
+  url 'http://scrapietest/test'
+  attributes({ 'foo' => '.foo' })
+end
+
+class ParamsScrapie < Scrapie
+  url 'http://scrapietest/test_with_params'
+  params({ :test_param => 'test_param_for_getting' })
+  attributes({
+    'param' => 'div#param',
+    'param_upcased' => 'div#param_upcased'
+  })
+end
+
+class FourOhFourScrapie < Scrapie
+  url 'http://scrapietest/ends_of_the_earth'
+  attributes({
+    'results' => 'div#post_param'
+  })
+end
+
+class FiveHundredScrapie < Scrapie
+  url 'http://scrapietest/500'
+  attributes({
+    'results' => 'div#post_param'
+  })
+end
+
+class PostScrapie < Scrapie
+  url 'http://scrapietest/post'
+  http_method :post
+  
+  params({ :search => 'le_post' })
+  attributes({
+    'results' => 'div#post_param'
+  })
+end
+
+describe Scrapie do
+  
+  it 'whines if you don\'t specify any attributes' do
+    lambda { nas = NoAttributeScrapie.find(:har => 'heh') }.should raise_error(Scrapie::NoAttributesException)
+  end
+  
+  it 'does a basic fetch sans params' do
+    basic = BasicScrapie.find
+    basic.foo.should == 'example'
+  end
+  
+  it 'handles params' do
+    test_string = 'sdkfjhdsafjkladhfklzxcv123' # todo: random string
+    
+    paramtest = ParamsScrapie.find(:test_param => test_string)
+    paramtest.param.should == test_string
+    paramtest.param_upcased.should == test_string.upcase
+  end
+  
+  it 'handles 404s' do
+    lambda { nas = FourOhFourScrapie.find(:har => 'heh') }.should raise_error(Mechanize::ResponseCodeError)
+  end
+  it 'handles 500s' do
+    lambda { nas = FiveHundredScrapie.find(:har => 'heh') }.should raise_error(Mechanize::ResponseCodeError)
+  end
+  it 'uses different HTTP methods' do
+    post = PostScrapie.find(:search => 'le_search')
+    
+    post.results.should == 'le_search'
+  end
+  
+  it 'uses a before_fetch'
+  it 'uses an after_fetch'
+  it 'sets agent options'
+
+end

metadata

@@ -0,0 +1,139 @@
+--- !ruby/object:Gem::Specification
+name: scrapie
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- Adrian Pike
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-10-26 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: &2152794940 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2152794940
+- !ruby/object:Gem::Dependency
+  name: sham_rack
+  requirement: &2152794360 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2152794360
+- !ruby/object:Gem::Dependency
+  name: sinatra
+  requirement: &2152793740 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2152793740
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &2152791580 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2152791580
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: &2152790880 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: *2152790880
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: &2152790220 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.4
+  type: :development
+  prerelease: false
+  version_requirements: *2152790220
+- !ruby/object:Gem::Dependency
+  name: rcov
+  requirement: &2152789620 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2152789620
+description: ! 'Scrapie is a tool that allows you to really simply and quickly fab
+  up a class that translates CSS selectors into attributes, and lets you specify your
+  own translations on query params. '
+email: adrian@pikeapps.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.rdoc
+files:
+- .document
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/scrapie.rb
+- spec/helper.rb
+- spec/scrapie_spec.rb
+homepage: http://github.com/adrianpike/scrapie
+licenses:
+- MIT
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
+      - 0
+      hash: 4604187453020345507
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Scrapie scrapes things for great justice.
+test_files: []