outlander 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6b6951e27ebb022fbc2ec65a1b7394e84d876868
+  data.tar.gz: d77d4077c1cbdca9a6c09980c12016a9639b05d4
+SHA512:
+  metadata.gz: 0a4ceb2e8a3e564db5ec088855428711e66a63e903f35c58ed18f127cea3eebea2fa7af673b872494dceffdbc54c7672f21dc78a8f5ff276d9df4fe5106ce2e4
+  data.tar.gz: 2da3b6e9e6939c0032004ef4fa71fea7d7ed2f65f6c20907bbfa318a7864beee8195c76821023f588669d8b1f355d8b3944c76d126584e3d1fe0f12caa010f27

data/.gitignore

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

data/Gemfile

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

data/README.md

@@ -0,0 +1,36 @@
+# Outlander
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/outlander`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'outlander'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install outlander
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/outlander.
+

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "outlander"
+
+# 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(__FILE__)

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/outlander/agent.rb

@@ -0,0 +1,41 @@
+require 'httparty'
+
+module Outlander
+
+  class Agent
+
+    include HTTParty
+
+    class << self
+      attr_accessor :cache_storage
+    end
+
+    def self.fetch(path, options = {}, &block)
+      if cache_enabled? && options[:cache]
+        response_body = @cache_storage.get(path) || get(path, options, &block).body
+        @cache_storage.set(path, response_body)
+        response_body
+      else
+        get(path, options, &block).body
+      end
+    end
+
+    def self.method_missing(m, *args, &block)
+      if m.to_s.end_with? '_with_cache'
+        if cache_enabled?
+          response_body = @cache_storage.get(args[0]) || get(*args, &block).body
+          @cache_storage.set(args[0], response_body)
+          response_body
+        else
+          get(*args, &block).body
+        end
+      end
+    end
+
+    private
+
+    def self.cache_enabled?
+      !!@cache_storage
+    end
+  end
+end

data/lib/outlander/crawler.rb

@@ -0,0 +1,88 @@
+require 'nokogiri'
+require 'logger'
+require 'outlander/agent'
+require 'outlander/threads_pool'
+
+module Outlander
+
+  module Crawler
+
+    DEFAULT_OPTIONS = {
+      num_threads: 3
+    }
+
+    class << self
+      def included(base)
+        base.extend ClassMethods
+
+        base.class_eval do
+          @roots = {}
+          @handlers = {}
+        end
+      end
+    end
+
+    module ClassMethods
+
+      attr_reader :roots, :setup, :handlers
+
+      def entrypoint(url, handler = :process_root)
+        @roots[url] = handler
+      end
+
+      def before_start(&block)
+        @setup = block
+      end
+
+      def method_missing(m, *args, &block)
+        if m.to_s.start_with? 'process_'
+          @handlers[m] = block
+        else
+          super
+        end
+      end
+    end
+
+    def initialize(options = {})
+      agent.cache_storage = options.delete(:cache_storage)
+      @logger = Logger.new(options.fetch(:log_to, STDOUT))
+      @options = options.merge DEFAULT_OPTIONS
+      @history = {}
+      @pool = ThreadsPool.new @options[:num_threads]
+      self.class.roots.each do |url, handler|
+        enqueue url, handler
+      end
+    end
+
+    def run!(&block)
+      @result_handler = block
+      instance_eval &self.class.setup
+      @pool.start
+    end
+
+    private
+
+    def record(data)
+      @result_handler.call data
+    end
+
+    def enqueue(url, handler, *args)
+      return if @history[url] == handler
+      @pool.enqueue do
+        begin
+          body = agent.get_with_cache(url)
+          instance_exec Nokogiri::HTML(body), *args, &self.class.handlers[handler.to_sym]
+        rescue => e
+          @logger.error "Failed to process #{url} with ##{handler} #{e.inspect}"
+        else
+          @logger.info "Processed #{url} with ##{handler}"
+        end
+      end
+      @logger.info "Enqueued #{url} for ##{handler}"
+    end
+
+    def agent
+      @agent ||= Agent.dup
+    end
+  end
+end

data/lib/outlander/threads_pool.rb

@@ -0,0 +1,34 @@
+require 'thread'
+
+module Outlander
+
+  class ThreadsPool
+
+    def initialize(num_threads = 3)
+      @num_threads = num_threads
+      @queue = Queue.new
+    end
+
+    def enqueue(&task)
+      @queue << task
+    end
+
+    def start
+      raise "Could not start with empty queue" if @queue.empty?
+      run_threads(@num_threads)
+      sleep 1 until @queue.empty? && @queue.num_waiting == @num_threads
+    end
+
+    private
+
+    def run_threads(num_threads = 1)
+      1.upto(num_threads) do
+        Thread.new do
+          while task = @queue.pop
+            task.call
+          end
+        end
+      end
+    end
+  end
+end

data/lib/outlander/version.rb

@@ -0,0 +1,3 @@
+module Outlander
+  VERSION = "0.1.0"
+end

data/lib/outlander.rb

@@ -0,0 +1,3 @@
+require "outlander/version"
+
+require 'outlander/crawler'

data/outlander.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'outlander/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "outlander"
+  spec.version       = Outlander::VERSION
+  spec.authors       = ["Terry Progetto"]
+  spec.email         = ["terryprogetto@gmail.com"]
+
+  spec.summary       = %q{Web pages crawler.}
+  spec.description   = %q{Multithreaded web crawler with transparent DSL and requests caching.}
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.14"
+  spec.add_development_dependency "rake", "~> 10.0"
+
+  spec.add_dependency "httparty"
+  spec.add_dependency "nokogiri"
+  spec.add_dependency "dalli"
+end

metadata

@@ -0,0 +1,128 @@
+--- !ruby/object:Gem::Specification
+name: outlander
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Terry Progetto
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-05-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+- !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: httparty
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  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: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: dalli
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Multithreaded web crawler with transparent DSL and requests caching.
+email:
+- terryprogetto@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".DS_Store"
+- ".gitignore"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/.DS_Store
+- lib/outlander.rb
+- lib/outlander/.DS_Store
+- lib/outlander/agent.rb
+- lib/outlander/crawler.rb
+- lib/outlander/threads_pool.rb
+- lib/outlander/version.rb
+- outlander.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: 2.6.11
+signing_key: 
+specification_version: 4
+summary: Web pages crawler.
+test_files: []