rubychan 0.1.1

data/.document

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

data/.rspec

@@ -0,0 +1 @@
+--color

data/.rvmrc

@@ -0,0 +1 @@
+rvm default@rubychan

data/.travis.yml

@@ -0,0 +1,2 @@
+language: ruby
+rvm: 1.9.2

data/Gemfile

@@ -0,0 +1,18 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+gem "thor"
+gem "nokogiri"
+gem "fakeweb"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "rspec", "~> 2.8.0"
+  gem "rdoc", "~> 3.12"
+  gem "cucumber", ">= 0"
+  gem "bundler", "~> 1.0.0"
+  gem "jeweler", "~> 1.8.3"
+  gem "simplecov", ">= 0"
+end

data/Gemfile.lock

@@ -0,0 +1,54 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    builder (3.0.0)
+    cucumber (1.1.9)
+      builder (>= 2.1.2)
+      diff-lcs (>= 1.1.2)
+      gherkin (~> 2.9.0)
+      json (>= 1.4.6)
+      term-ansicolor (>= 1.0.6)
+    diff-lcs (1.1.3)
+    fakeweb (1.3.0)
+    gherkin (2.9.0)
+      json (>= 1.4.6)
+    git (1.2.5)
+    jeweler (1.8.3)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+      rdoc
+    json (1.6.5)
+    multi_json (1.1.0)
+    nokogiri (1.5.2)
+    rake (0.9.2.2)
+    rdoc (3.12)
+      json (~> 1.4)
+    rspec (2.8.0)
+      rspec-core (~> 2.8.0)
+      rspec-expectations (~> 2.8.0)
+      rspec-mocks (~> 2.8.0)
+    rspec-core (2.8.0)
+    rspec-expectations (2.8.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.8.0)
+    simplecov (0.6.1)
+      multi_json (~> 1.0)
+      simplecov-html (~> 0.5.3)
+    simplecov-html (0.5.3)
+    term-ansicolor (1.0.7)
+    thor (0.14.6)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.0.0)
+  cucumber
+  fakeweb
+  jeweler (~> 1.8.3)
+  nokogiri
+  rdoc (~> 3.12)
+  rspec (~> 2.8.0)
+  simplecov
+  thor

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2012 Blaine Pace
+
+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 +1,19 @@
+= rubychan
+
+RubyChan is a command line tool and library for scraping 4Chan threads.
+
+== Contributing to rubychan
+ 
+* 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) 2012 Blaine Pace. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,52 @@
+# 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 = "rubychan"
+  gem.homepage = "http://github.com/sensae/rubychan"
+  gem.license = "MIT"
+  gem.summary = %Q{4Chan Scraping Toolkit}
+  gem.description = %Q{A script and library for scraping 4chan threads}
+  gem.email = "blainepace@gmail.com"
+  gem.authors = ["Blaine Pace"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+require 'cucumber/rake/task'
+Cucumber::Rake::Task.new(:features)
+
+task :default => :spec
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "rubychan #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.1

data/bin/rubychan

@@ -0,0 +1,5 @@
+#!/usr/bin/env ruby
+
+require 'rubychan'
+
+RubyChan::Runner.start

data/features/rubychan.feature

@@ -0,0 +1,8 @@
+Feature: Scraping 4chan
+  In order to scrape 4chan
+  A user presents a URI to a thread
+
+  Scenario: Scraping a URI
+    Given a valid URI
+    When I call scrape
+    Then I should see output

data/features/step_definitions/rubychan_steps.rb

@@ -0,0 +1,21 @@
+Given /^a valid URI$/ do
+  @uri = "http://4chan.org"
+  @html = <<-eos
+    <html>
+      <body>
+        <a href="http://images.4chan.org/a/src/1.jpg"></a>
+        <a href="http://images.4chan.org/b/src/2.jpg"></a>
+      </body>
+    </html>
+  eos
+  FakeWeb.register_uri(:get, "http://4chan.org", :body => @html)
+end
+
+When /^I call scrape$/ do
+  @runner = RubyChan::Runner.new
+  @runner.scrape(@uri)
+end
+
+Then /^I should see output$/ do
+  STDOUT.should_not be_nil
+end

data/features/support/env.rb

@@ -0,0 +1,17 @@
+require 'fakeweb'
+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
+
+STDOUT = $stdout = StringIO.new
+STDERR = $stderr = StringIO.new
+
+$LOAD_PATH.unshift(File.dirname(__FILE__) + '/../../lib')
+require 'rubychan'
+
+require 'rspec/expectations'

data/lib/rubychan.rb

@@ -0,0 +1,14 @@
+require 'thor'
+
+require 'scraper'
+
+module RubyChan
+  class Runner < Thor
+
+    desc "Scrape URL", "Scrape a 4chan URL"
+    def scrape(uri)
+      @scraper = RubyChan::Scraper.new(uri)
+      @scraper.scrape
+    end
+  end
+end

data/lib/scraper.rb

@@ -0,0 +1,27 @@
+require 'open-uri'
+require 'nokogiri'
+
+module RubyChan
+  class Scraper
+
+    def initialize(uri)
+      @uri = uri
+    end
+
+    def scrape
+      doc = Nokogiri::HTML(open(@uri))
+      doc.xpath('//a').each do |link|
+        if(link['href'] =~ /\/\/images.4chan.org\/.+\/src\/\d+\..../)
+          uri = URI(link['href'])
+          puts "Downloading #{uri}"
+          Net::HTTP.start(uri.host) do |http|
+            resp = http.get(uri.path)
+            open(File.basename(uri.path), "wb") do |file|
+              file.write(resp.body)
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/spec/rubychan_spec.rb

@@ -0,0 +1,25 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "Rubychan" do
+  before :each do
+    @runner = RubyChan::Runner.new
+    @scraper = mock("Scraper").as_null_object
+    RubyChan::Scraper.stub!(:new).and_return(@scraper)
+    @uri = "http://4chan.org"
+  end
+
+  context "#scrape" do
+
+    it "should scrape a URI" do
+      @scraper.should_receive(:scrape)
+      @runner.scrape(@uri)
+    end
+
+    it "should print imagelinks" do
+      @imagelinks = "Image Links!"
+      @scraper.stub!(:imagelinks).and_return(@imagelinks)
+      STDOUT.should_receive(:puts).with(@imagelinks)
+      @runner.scrape(@uri)
+    end
+  end
+end

data/spec/scraper_spec.rb

@@ -0,0 +1,29 @@
+require 'spec_helper'
+require 'fakeweb'
+
+describe RubyChan::Scraper do
+
+  before :each do
+    @uri = "http://4chan.org"
+    @html = <<-eos
+      <html>
+        <body>
+          <a href="http://images.4chan.org/a/src/1.jpg"></a>
+          <a href="http://images.4chan.org/b/src/2.jpg"></a>
+        </body>
+      </html>
+    eos
+    FakeWeb.register_uri(:get, "http://4chan.org", :body => @html)
+    @scraper = RubyChan::Scraper.new(@uri)
+  end
+
+  it "should open a URI" do
+    @scraper.should_receive(:open).with(@uri)
+    @scraper.scrape
+  end
+
+  it "should extract image URIs from the page source" do
+    @scraper.scrape
+    @scraper.imagelinks.should =~ /http:\/\/images.4chan.org\/.\/src\/.+/
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,15 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'rspec'
+require 'rubychan'
+
+STDOUT = $stdout = StringIO.new
+STDERR = $stderr = StringIO.new
+
+# Requires supporting files with custom matchers and macros, etc,
+# in ./support/ and its subdirectories.
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
+
+RSpec.configure do |config|
+
+end

metadata

@@ -0,0 +1,169 @@
+--- !ruby/object:Gem::Specification
+name: rubychan
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+  prerelease: 
+platform: ruby
+authors:
+- Blaine Pace
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-16 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: &70172203969060 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70172203969060
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &70172203966900 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70172203966900
+- !ruby/object:Gem::Dependency
+  name: fakeweb
+  requirement: &70172203964980 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70172203964980
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70172203961940 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.8.0
+  type: :development
+  prerelease: false
+  version_requirements: *70172203961940
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: &70172203944300 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: *70172203944300
+- !ruby/object:Gem::Dependency
+  name: cucumber
+  requirement: &70172203941560 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70172203941560
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: &70172203928560 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: *70172203928560
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: &70172203926840 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.8.3
+  type: :development
+  prerelease: false
+  version_requirements: *70172203926840
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: &70172203921980 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70172203921980
+description: A script and library for scraping 4chan threads
+email: blainepace@gmail.com
+executables:
+- rubychan
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.rdoc
+files:
+- .document
+- .rspec
+- .rvmrc
+- .travis.yml
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- VERSION
+- bin/rubychan
+- features/rubychan.feature
+- features/step_definitions/rubychan_steps.rb
+- features/support/env.rb
+- lib/rubychan.rb
+- lib/scraper.rb
+- spec/rubychan_spec.rb
+- spec/scraper_spec.rb
+- spec/spec_helper.rb
+homepage: http://github.com/sensae/rubychan
+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: 165603134148496118
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.6
+signing_key: 
+specification_version: 3
+summary: 4Chan Scraping Toolkit
+test_files: []