ranunculus 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 92b1b11c7cdbeca56636d6da9a841d02506b95e9
+  data.tar.gz: 84b35bb769296e265f7bfdb8256fef3ebc6f8719
+SHA512:
+  metadata.gz: 96ab0a4bc0ae61ac78e1cc7b6bef8b2ad88a5f9327f3f3237966d72ef2f1d31e4c9744f89abe02a864c5abbcc42dcd40fcf84ddb6e316898881c4fd0efb17f2a
+  data.tar.gz: b7ba1eebbfc008ddd8b4a356249c7a78cf9547e2cc8fcf19e2c92e341919c17174b3952bab40f0a5cb5d3385e87d8e639e265843f5f09f0ec25c9f45c894777e

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.3.0
+before_install: gem install bundler -v 1.11.2

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at TODO: Write your email address. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in ranunculus.gemspec
+gemspec

data/README.md

@@ -0,0 +1,49 @@
+# Ranunculus
+
+Another Web crawler running with Amazon SQS and ElastiCache(Redis).
+You need a worker which is available at GitHub.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ranunculus'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ranunculus
+
+## Usage
+
+    require 'aws-sdk'
+    require 'redis'
+    require 'ranunculus'
+
+    sqs = Aws::SQS::Client.new(
+      access_key_id: ENV['ACCESS_KEY_ID'],
+      secret_access_key: ENV['SECRET_ACCESS_KEY'],
+      region: 'ap-northeast-1'
+    )
+    redis = Redis.new(:host => "localhost", :port => 6379, :db => 0)
+
+    URL_QUEUE_URL = "https://sqs.ap-northeast-1.amazonaws.com/12345/UrlQueue"
+    RESULT_QUEUE_URL = "https://sqs.ap-northeast-1.amazonaws.com/12345/ResultQueue"
+
+    c = Ranunculus::Crawler.new(sqs, redis, URL_QUEUE_URL, RESULT_QUEUE_URL)
+
+    page = Ranunculus::Page.new("http://www.yahoo.com")
+    c.on_every_page do |page|
+      puts page.url
+    end
+    c.start(page, 1, "Ranunculus")
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/k-kawa/ranunculus-ruby. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+

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/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "ranunculus"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/ranunculus.rb

@@ -0,0 +1,5 @@
+require 'aws-sdk-core'
+
+require "ranunculus/version.rb"
+require "ranunculus/page"
+require "ranunculus/crawler"

data/lib/ranunculus/crawler.rb

@@ -0,0 +1,104 @@
+class Ranunculus::Crawler
+
+  attr :user_agent
+
+  def initialize(sqs, redis, job_queue_url, result_queue_url)
+    @sqs = sqs
+    @redis = redis
+    @job_queue_url = job_queue_url
+    @result_queue_url = result_queue_url
+
+    @on_every_page_blocks = []
+
+    @result_count = 0
+    @result_pages = {}
+    @pushed_urls = {}
+    @skip_patterns = []
+  end
+
+  def skip_if(patterns)
+    @skip_patterns = patterns
+  end
+
+  def skip?(url)
+    @skip_patterns.any? do |pattern|
+      url.match(pattern) != nil
+    end || visit_link?(url)
+  end
+
+  def start(page, max_depth, user_agent)
+    @max_depth = max_depth
+    @user_agent = user_agent
+    
+    @pushed_urls[page.url] = 1
+    @sqs.send_message({
+                        queue_url: @job_queue_url,
+                        message_body: page.to_sqs_hash(self).to_json,
+                      })
+
+    while @result_count < @pushed_urls.size
+      work
+    end
+  end
+
+  def work
+    queue_resp = @sqs.receive_message({
+                                        queue_url: @result_queue_url,
+                                        wait_time_seconds: 20,
+                                        visibility_timeout: 10,
+                                        max_number_of_messages: 1
+                                      })
+    return if queue_resp.messages.length == 0
+    message_body   = queue_resp.messages[0].body
+    receipt_handle = queue_resp.messages[0].receipt_handle
+    @result_count += 1
+
+    queue_obj = JSON.parse(message_body)
+    body = if queue_obj['HasBody']
+             @redis.get(queue_obj['Url'])
+           else
+             nil
+           end
+    
+    @sqs.delete_message({
+                          queue_url: @result_queue_url,
+                          receipt_handle: receipt_handle
+                        })
+
+    unless body.nil? || body.size == 0
+      page = Ranunculus::Page.create_from_queue(queue_obj, body)
+      @result_pages[page.url] = page
+      
+      urls = page.fetch_urls.delete_if{|url| skip?(url)}
+      if page.depth < @max_depth
+        urls.each do |url|
+          @pushed_urls[url] = 1
+          @sqs.send_message({
+                              queue_url: @job_queue_url,
+                              message_body: Ranunculus::Page.
+                                new(url, page.depth+1).
+                                to_sqs_hash(self).to_json
+                            })
+        end
+      end
+
+      do_page_blocks page
+      page.discard_doc!
+    end
+  end
+
+  def on_every_page(&block)
+    @on_every_page_blocks << block
+    self
+  end
+
+  def visit_link?(url)
+    @pushed_urls.key?(url)
+  end
+
+  def do_page_block(page)
+    @on_every_page_blocks.each do |block|
+      block.call(page)
+    end
+  end
+end

data/lib/ranunculus/page.rb

@@ -0,0 +1,70 @@
+class Ranunculus::Page
+
+  attr :url, :depth, :body
+  
+  def self.create_from_queue(sqs_result, body)
+    new(
+      sqs_result['Url'],
+      sqs_result['Depth'],
+      body
+    )
+  end
+  
+  def initialize(url, depth = 0, body = nil)
+    @url = url
+    @depth = depth
+    @body = body
+
+    @links = nil
+  end
+
+  def crawl(cralwer)
+    crawler.start(self)
+  end
+
+  def to_sqs_hash(cralwer)
+    {
+      "Url" => @url,
+      "Depth" => @depth,
+      "Headers": {"User-Agent"=> cralwer.user_agent}
+    }
+  end
+
+  def doc
+    return nil if @body.nil?
+    return @doc unless @doc.nil?
+    @doc = Nokogiri::HTML(@body)
+  end
+
+  def discard_doc!
+    @doc = nil
+  end
+
+  def fetch_urls
+    return @links unless @links.nil?
+    @links = []
+
+    doc.search("//a[@href]").each do |a|
+      u = a['href']
+      next if u.nil? or u.empty?
+      abs = to_absolute(u)
+      unless abs.nil?
+        @links << abs
+      end
+    end
+    @links.uniq!
+    @links
+  end
+
+  def to_absolute(link)
+    return nil if link.nil?
+    return nil if link.start_with?("mail")
+    relative = URI.parse(link.to_s.gsub(/#[a-zA-Z0-9_-]*$/,''))
+    absolute = URI(@url).merge(relative)
+    absolute.path = '/' if absolute.path.nil?
+    absolute
+  rescue URI::InvalidURIError, URI::InvalidComponentError, URI::BadURIError
+    # Not sure they are the all of the errors that can happen when the given link is invalid....
+    return nil
+  end
+end

data/lib/ranunculus/version.rb

@@ -0,0 +1,3 @@
+module Ranunculus
+  VERSION = "0.1.1"
+end

data/ranunculus.gemspec

@@ -0,0 +1,40 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ranunculus/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ranunculus"
+  spec.version       = Ranunculus::VERSION
+  spec.authors       = ["Kohei KAWASAKI"]
+  spec.email         = []
+
+  spec.summary       = %q{Another Web crawler running with Amazon SQS and ElastiCache(Redis)}
+  spec.description   = %q{}
+  spec.homepage      = ""
+
+  # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
+  # delete this section to allow pushing this gem to any host.
+  if spec.respond_to?(:metadata)
+    # spec.metadata['allowed_push_host'] = "http://localhost.com'"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "byebug"
+  spec.add_development_dependency "pry-doc"
+  spec.add_development_dependency "pry-byebug"
+  spec.add_development_dependency "pry-rails"
+  spec.add_development_dependency "pry-stack_explorer"
+
+  spec.add_dependency "nokogiri", ">= 1.3.0"
+  spec.add_dependency "aws-sdk", "~> 2"
+  spec.add_dependency "redis", "~>3.2"
+end

metadata

@@ -0,0 +1,211 @@
+--- !ruby/object:Gem::Specification
+name: ranunculus
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Kohei KAWASAKI
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-04-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry-doc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry-byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry-rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry-stack_explorer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+- !ruby/object:Gem::Dependency
+  name: aws-sdk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+- !ruby/object:Gem::Dependency
+  name: redis
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+description: ''
+email: []
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/ranunculus.rb
+- lib/ranunculus/crawler.rb
+- lib/ranunculus/page.rb
+- lib/ranunculus/version.rb
+- ranunculus.gemspec
+homepage: ''
+licenses: []
+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: 2.4.5.1
+signing_key: 
+specification_version: 4
+summary: Another Web crawler running with Amazon SQS and ElastiCache(Redis)
+test_files: []
+has_rdoc: