crabbs 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9fc5a904a6d962205d1a075c95ef79a98ccba4e7
+  data.tar.gz: e30f07bf9305c2e4a6aad06de1c335d2f2976d0d
+SHA512:
+  metadata.gz: 82c05e3734be530a5f8e9059fdd69959598f76ad66cbd3ce2cb9af7120e3d24cc9839eb79a7168417273404e7dd20a74a1cad01d05563f5ce4743f59e6efaaba
+  data.tar.gz: db18939b31a5cb899cdc8ca5872ba355e21ef3f597106c9996debc44697fa08ab8c7d1834bbbdff0c3373939c034334e5897a514ab0a45a2b9c91c8410d584fa

data/.gitignore

@@ -0,0 +1,25 @@
+*.swa
+*.swo
+*.swp
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

@@ -0,0 +1,3 @@
+--color
+--format documentation
+--warnings

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Bruno Trecenti
+
+MIT License
+
+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.md

@@ -0,0 +1,25 @@
+# Crabbs
+
+A simple web crawler
+
+## Description
+
+A simple web crawler for single domains that oupts a site map as json
+
+## Installation
+
+`gem install crabbs`
+
+## Usage
+
+`crabbs -u http://example.com`
+
+Please reference to `crabbs --help` for further options.
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/crabbs/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/crabbs

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+
+require 'crabbs'
+
+cli = Crabbs::CLI.new
+cli.start

data/crabbs.gemspec

@@ -0,0 +1,29 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'crabbs/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'crabbs'
+  spec.version       = Crabbs::VERSION
+  spec.authors       = ['Bruno Trecenti']
+  spec.email         = ['btrecent@thoughtworks.com']
+  spec.summary       = %q{A crawler for the web}
+  spec.description   = %q{A crawler for a single domain web application}
+  spec.homepage      = 'http://github.com/Trecenti/crabbs'
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.add_runtime_dependency 'nokogiri', '~> 1.6'
+  spec.add_runtime_dependency 'slop', '~> 3.5', '>= 3.5.0'
+
+  spec.add_development_dependency 'bundler', '~> 1.6'
+  spec.add_development_dependency 'rake', '~> 10.3', '>= 10.3.2'
+  spec.add_development_dependency 'rspec', '~> 2.14', '>= 2.14.1'
+  spec.add_development_dependency 'webmock', '~> 1.18', '>= 1.18.0'
+  spec.add_development_dependency 'pry', '~> 0.9', '>= 0.9.12'
+end

data/lib/crabbs/cli.rb

@@ -0,0 +1,27 @@
+require 'slop'
+require 'json'
+
+module Crabbs
+  class CLI
+
+    def start
+      begin
+        opts = parse_options
+        result = Crabbs.start(opts[:url])
+        STDOUT.puts result.to_json
+      rescue Slop::MissingOptionError => e
+        STDOUT.puts e.message
+      end
+    end
+
+    private
+
+    def parse_options
+      Slop.parse(help: true) do
+        banner 'Usage: crabbs [options]'
+
+        on 'u', 'url=', 'URL to start crawling', required: true
+      end
+    end
+  end
+end

data/lib/crabbs/crawler.rb

@@ -0,0 +1,42 @@
+require 'net/http'
+
+module Crabbs
+  class Crawler
+    attr_reader :visited, :site_map
+
+    def initialize()
+      @visited = []
+      @site_map = {}
+    end
+
+    def crawl(uri_string)
+      recurse uri_string, @site_map
+    end
+
+    private
+
+    def recurse(uri_string, hash)
+      hash[uri_string] = Hash.new
+
+      return if (@visited.include? uri_string)
+
+      links = extract_links uri_string
+      @visited << uri_string
+
+      links.each do |link|
+        recurse(link, hash[uri_string])
+      end
+    end
+
+    def extract_links(uri_string)
+      begin
+        uri = URI.parse(uri_string)
+        page = Crabbs::Page.new(Net::HTTP.get(uri), uri.to_s)
+
+        page.links
+      rescue URI::InvalidURIError
+        []
+      end
+    end
+  end
+end

data/lib/crabbs/page.rb

@@ -0,0 +1,45 @@
+require 'nokogiri'
+
+module Crabbs
+  class Page
+    def initialize(html, url)
+      @html = Nokogiri::HTML(html)
+      @url = url
+    end
+
+    def links
+      uri_list = @html.css('a[href]').map { |a| URI.parse(a['href']) }
+
+      valid_uris = uri_list
+        .select { |uri| uri.host == URI.parse(@url).host or uri.host.nil? }
+        .select { |uri| uri.fragment.nil? or not uri.fragment.empty? }
+
+      links = create_full_uri_links(valid_uris)
+
+      links = links.select do |link|
+        host = URI.parse(link).host
+        extension = File.extname(link.sub(host, ''))
+        extension.empty? or extension == '.html'
+      end
+
+      links.uniq
+    end
+
+    private
+
+    def create_full_uri_links(uri_list)
+      uri_list.map do |uri|
+        new_uri = uri
+
+        if uri.host.nil?
+          new_uri = URI.parse @url
+          new_uri = URI.join(new_uri.to_s, uri.path) unless uri.path.nil?
+          new_uri = URI.join(new_uri.to_s, "?#{uri.query}") unless uri.query.nil?
+          new_uri = URI.join(new_uri.to_s, "##{uri.fragment}") unless uri.fragment.nil?
+        end
+
+        new_uri.to_s
+      end
+    end
+  end
+end

data/lib/crabbs/version.rb

@@ -0,0 +1,3 @@
+module Crabbs
+  VERSION = "0.0.2"
+end

data/lib/crabbs.rb

@@ -0,0 +1,17 @@
+require 'crabbs/version'
+require 'crabbs/page'
+require 'crabbs/crawler'
+require 'crabbs/cli'
+
+module Crabbs
+
+  class << self
+    attr_reader :crawler
+
+    def start(url)
+      @crawler = Crabbs::Crawler.new
+      @crawler.crawl url
+      @crawler.site_map
+    end
+  end
+end

data/spec/crabbs/cli_spec.rb

@@ -0,0 +1,33 @@
+require 'crabbs/cli'
+
+describe Crabbs::CLI do
+  subject { Crabbs::CLI.new }
+
+  describe '#start' do
+    context 'with no arguments' do
+      it 'prints out help' do
+        ARGV.replace []
+
+        allow(STDOUT).to receive(:puts)
+
+        subject.start
+
+        expect(STDOUT).to have_received(:puts).with('Missing required option(s): url')
+      end
+    end
+
+    context 'with required arguments' do
+      it 'outputs the result' do
+        ARGV.replace ['--url=https://example.com']
+
+        allow(Crabbs).to receive(:start).and_return('result')
+        allow(STDOUT).to receive(:puts)
+
+        subject.start
+
+        expect(Crabbs).to have_received(:start).with('https://example.com')
+        expect(STDOUT).to have_received(:puts).with('result'.to_json)
+      end
+    end
+  end
+end

data/spec/crabbs/crabbs_spec.rb

@@ -0,0 +1,17 @@
+require 'webmock/rspec'
+require 'crabbs'
+
+describe Crabbs do
+
+  subject { Crabbs }
+
+  describe '#start' do
+    before do
+      stub_request(:get, "http://example.com/").to_return(:body => "")
+    end
+
+    it 'starts crawling' do
+      subject.start('http://example.com').should == { 'http://example.com' => {} }
+    end
+  end
+end

data/spec/crabbs/crawler_spec.rb

@@ -0,0 +1,88 @@
+require 'webmock/rspec'
+require 'json'
+require 'crabbs/crawler'
+
+describe Crabbs::Crawler do
+  describe '#crawl' do
+    subject { Crabbs::Crawler.new }
+
+    context 'an invalid URI' do
+      it 'stores single entry site map' do
+        subject.crawl %q{invalid\uri}
+
+        subject.site_map.should == {"invalid\\uri"=>{}}
+      end
+    end
+
+    context 'a valid URI' do
+      context 'non html response' do
+        before do
+          @uri_string = 'http://example.com/test.json'
+          stub_request(:get, @uri_string).to_return(body: { a: { href: '/test' } }.to_json, headers: { 'Content-Type' => 'application/json' })
+        end
+
+        it 'stores empty hash map' do
+          subject.crawl @uri_string
+
+          subject.site_map.should == { 'http://example.com/test.json' => {} }
+        end
+      end
+
+      context 'without recursive links' do
+        before do
+          @uri_string = 'http://example.com/'
+          stub_request(:get, @uri_string).to_return(body: %Q{<a href="/path"></a><a href="/local"></a><a href="http://fb.com/"></a>})
+          stub_request(:get, "http://example.com/path").to_return(body: "")
+          stub_request(:get, "http://example.com/local").to_return(body: "")
+        end
+
+        it 'stores the visted links' do
+          subject.crawl @uri_string
+
+          subject.visited.should include('http://example.com/')
+        end
+
+        it 'stores a hash with the site map' do
+          subject.crawl @uri_string
+
+          expected_site_map = {
+            'http://example.com/' => {
+              'http://example.com/path' => {},
+              'http://example.com/local' => {}
+            }
+          }
+
+          subject.site_map.should == expected_site_map
+        end
+      end
+
+      context 'with recursive links' do
+        before :each do
+          @uri_string = 'http://example.com/'
+          stub_request(:get, @uri_string).to_return(body: %Q{<a href="/path"></a>})
+          stub_request(:get, "http://example.com/path").to_return(body: %Q{<a href="http://example.com/"></a>})
+        end
+
+        it 'visits both pages' do
+          subject.crawl @uri_string
+
+          subject.visited.should == ['http://example.com/', 'http://example.com/path']
+        end
+
+        it 'stores a hash with the site map' do
+          subject.crawl @uri_string
+
+          expected_site_map = {
+            'http://example.com/' => {
+              'http://example.com/path' => {
+                'http://example.com/' => {}
+              }
+            }
+          }
+
+          subject.site_map.should == expected_site_map
+        end
+      end
+    end
+  end
+end

data/spec/crabbs/page_spec.rb

@@ -0,0 +1,79 @@
+require 'crabbs/page'
+
+describe Crabbs::Page do
+  describe '#links' do
+    let(:host) { 'http://localhost.com/' }
+
+    subject { Crabbs::Page.new(html, host) }
+
+    context 'when html has external links' do
+      let(:html) { %Q{<a href="http://facebook.com/"></a>} }
+
+      it 'ignores external links' do
+        subject.links.should be_empty
+      end
+    end
+
+    context 'when html has links for non html resources' do
+      let(:html) { %Q{<a href="http://localhost.com/path.zip"></a>} }
+
+      it 'ignores non html links' do
+        subject.links.should be_empty
+      end
+
+    end
+
+    context 'when html has links for subdomains' do
+      let(:html) { %Q{<a href="http://subdomain.localhost.com/path"></a>} }
+
+      it 'ignores subdomain links' do
+        subject.links.should be_empty
+      end
+    end
+
+    context 'when html has query parameter links' do
+      let(:html) { %Q{<a href="?path=1"></a><a href="?path=1"></a>} }
+
+      it 'includes the full uri link' do
+        subject.links.should == ['http://localhost.com/?path=1']
+      end
+    end
+
+    context 'when html has hash links' do
+      let(:html) { %Q{<a href="#path"></a><a href="#path"></a><a href="#"></a>} }
+
+      it 'includes the full uri link' do
+        subject.links.should == ['http://localhost.com/#path']
+      end
+
+      it 'ignore empty hashes' do
+        subject.links.should_not include('http://localhost.com/#')
+      end
+    end
+
+    context 'when html has direct path links' do
+      let(:host) { 'http://localhost.com/first/' }
+      let(:html) { %Q{<a href="path"></a><a href="path"></a>} }
+
+      it 'includes the full uri link' do
+        subject.links.should == ['http://localhost.com/first/path']
+      end
+    end
+
+    context 'when html has path links' do
+      let(:html) { %Q{<a href="/path"></a><a href="/path"></a>} }
+
+      it 'includes the full uri link' do
+        subject.links.should == ['http://localhost.com/path']
+      end
+    end
+
+    context 'when html has full URI links for the same host' do
+      let(:html) { %Q{<a href="http://localhost.com/path"></a><a href="/path"></a>} }
+
+      it 'includes the full uri link' do
+        subject.links.should == ['http://localhost.com/path']
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,194 @@
+--- !ruby/object:Gem::Specification
+name: crabbs
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Bruno Trecenti
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-05-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: slop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.5.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.5.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 10.3.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 10.3.2
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.14'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.14'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.18'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.18.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.18'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.18.0
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.12
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.12
+description: A crawler for a single domain web application
+email:
+- btrecent@thoughtworks.com
+executables:
+- crabbs
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/crabbs
+- crabbs.gemspec
+- lib/crabbs.rb
+- lib/crabbs/cli.rb
+- lib/crabbs/crawler.rb
+- lib/crabbs/page.rb
+- lib/crabbs/version.rb
+- spec/crabbs/cli_spec.rb
+- spec/crabbs/crabbs_spec.rb
+- spec/crabbs/crawler_spec.rb
+- spec/crabbs/page_spec.rb
+homepage: http://github.com/Trecenti/crabbs
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A crawler for the web
+test_files:
+- spec/crabbs/cli_spec.rb
+- spec/crabbs/crabbs_spec.rb
+- spec/crabbs/crawler_spec.rb
+- spec/crabbs/page_spec.rb