tjcrawler 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d862225dcccd8804520d59ed284c9e536eaed0c8
+  data.tar.gz: 5ce47b642a5bae952139f8ad53adb00d4f697e49
+SHA512:
+  metadata.gz: b376fdb73d63fe698ddd1dbb787ab3e5973a58fdc1e5c4514090c0785e3cf594dbbb3398d8b26dd555f255e899a70b1c3406aa741fe1af7273dae1913f8265e3
+  data.tar.gz: da0abd28dfb2245fd5b9a54d3e3094d4db1c8add13385eed00b13f15580d877a0ff22fd41e49c04e6c8361dead88f23edfd44d3c60e1592cad9bfb63f549c7ff

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 2.1.5

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Jian Weihang
+
+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 +1,31 @@
+# Tjcrawler
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'tjcrawler'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install tjcrawler
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/tjcrawler/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 +1,7 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec
+

data/examples/dsl.rb

@@ -0,0 +1,7 @@
+require 'tjcrawler'
+require 'pg'
+Tjcrawler.start_crawler do |config|
+  config.db_setting = {adapter: 'postgresql', database: 'fc2'}
+  config.css_selector = '.pager_box > a'
+  config.threads = 5
+end

data/examples/dsl_parser.rb

@@ -0,0 +1,9 @@
+require 'tjcrawler'
+require 'pg'
+Tjcrawler.start_parser do |config|
+  config.db_setting = {adapter: 'postgresql', database: 'fc2'}
+  config.threads = 3
+  config.proc = ->(doc){
+    true
+  }
+end

data/examples/fc2.rb

@@ -0,0 +1,15 @@
+require 'tjcrawler'
+require 'pg'
+
+ActiveRecord::Base.establish_connection(
+  adapter:  'postgresql',
+  database: 'fc2'
+)
+
+Tjcrawler::Page.enqueue 'http://video.fc2.com/list_scont/'
+
+threads = []
+5.times.each do
+  threads << Thread.new{ Tjcrawler::Crawler.new('.pager_box > a').start }
+end
+threads.each(&:join)

data/examples/fc2_parse.rb

@@ -0,0 +1,13 @@
+require 'tjcrawler'
+require 'pg'
+
+ActiveRecord::Base.establish_connection(
+  adapter:  'postgresql',
+  database: 'fc2'
+)
+
+parser = Tjcrawler::Parser.new{ |doc|
+  true
+}
+
+parser.start

data/examples/schema.rb

@@ -0,0 +1,15 @@
+require 'active_record'
+require 'pg'
+
+ActiveRecord::Base.establish_connection(
+  adapter:  'postgresql',
+  database: 'fc2'
+)
+
+ActiveRecord::Migration.create_table :pages, force: true do |t|
+  t.string :url
+  t.text :content
+  t.datetime :crawled_at
+  t.datetime :parsed_at
+  t.index :url, unique: true
+end

data/lib/tjcrawler.rb

@@ -0,0 +1,33 @@
+require 'tjcrawler/version'
+require 'tjcrawler/crawler'
+require 'tjcrawler/parser'
+require 'tjcrawler/config'
+
+module Tjcrawler
+  module_function
+  def start_crawler
+    config = Config.new
+    yield config
+    set_db(config)
+    threads = []
+    config.threads.times.each do
+      threads << Thread.new{ Tjcrawler::Crawler.new(config.css_selector).start }
+    end
+    threads.each(&:join)
+  end
+
+  def start_parser
+    config = Config.new
+    yield config
+    set_db(config)
+    threads = []
+    config.threads.times.each do
+      threads << Thread.new{ Tjcrawler::Parser.new(&config.proc).start }
+    end
+    threads.each(&:join)
+  end
+
+  def set_db config
+    ActiveRecord::Base.establish_connection config.db_setting
+  end
+end

data/lib/tjcrawler/config.rb

@@ -0,0 +1,8 @@
+module Tjcrawler
+  class Config
+    attr_accessor :db_setting, :css_selector, :threads, :proc
+    def initialize
+      @threads = 5
+    end
+  end
+end

data/lib/tjcrawler/crawler.rb

@@ -0,0 +1,30 @@
+require 'nokogiri'
+require 'open-uri'
+require 'tjcrawler/crawler/result'
+require 'tjcrawler/page'
+
+module Tjcrawler
+  class Crawler
+    def initialize css_selector_for_link_tags
+      @css = css_selector_for_link_tags
+    end
+
+    def crawl url
+      uri = URI(url).tap(&:normalize!)
+      content = open(uri).read
+      doc = Nokogiri::HTML(content)
+      links = doc.css(@css)
+      Result.new url: uri.to_s, content: content, links: links.map{|link| uri.merge(link[:href]).to_s}
+    end
+
+    def start
+      loop do
+        sleep 1 until page = Page.dequeue
+        print :'.'
+        result = crawl page.url
+        page.touch(:crawled_at) if page.update(content: result.content)
+        result.links.each{ |url| Page.enqueue url }
+      end
+    end
+  end
+end

data/lib/tjcrawler/crawler/result.rb

@@ -0,0 +1,12 @@
+module Tjcrawler
+  class Crawler
+    class Result
+      attr_accessor :url, :content, :links
+      def initialize(**params)
+        params.each do |key, value|
+          instance_variable_set("@#{key}", value) unless value.nil?
+        end
+      end
+    end
+  end
+end

data/lib/tjcrawler/page.rb

@@ -0,0 +1,18 @@
+require 'active_record'
+require 'active_support/core_ext/numeric/time'
+require 'active_support/core_ext/date/calculations'
+
+module Tjcrawler
+  class Page < ActiveRecord::Base
+    @@semaphore = Mutex.new
+    class << self
+      def enqueue url
+        @@semaphore.synchronize{Page.find_or_create_by url: url}
+      end
+
+      def dequeue
+        Page.where('crawled_at IS NULL OR crawled_at < ?', 1.day.ago).order('crawled_at IS NOT NULL, crawled_at').first
+      end
+    end
+  end
+end

data/lib/tjcrawler/parser.rb

@@ -0,0 +1,33 @@
+require 'nokogiri'
+require 'tjcrawler/page'
+
+module Tjcrawler
+  class Parser
+    # a nokogiri doc will be yield in block, return true/flase
+    # for successful/failed parsing.
+    def initialize &block
+      yield 'Block required' unless block_given?
+      @strategy = block
+    end
+
+    def parse content
+      doc = Nokogiri::HTML(content)
+      ret = @strategy[doc]
+      print :'.'
+      ret
+    end
+
+    def start
+      loop do
+        sleep 1 until page = find_next
+        page.touch(:parsed_at) if parse(page.content)
+      end
+    end
+
+    private
+
+    def find_next
+      Page.where('crawled_at IS NOT NULL AND (parsed_at IS NULL OR parsed_at < ?)', 1.day.ago).order('parsed_at IS NOT NULL, parsed_at').first
+    end
+  end
+end

data/lib/tjcrawler/scheduler.rb

@@ -0,0 +1,17 @@
+require 'tjcrawler/page'
+module Tjcrawler
+  class Scheduler
+    def start
+      @queue = Queue.new
+      @queue << @seed_url
+      @crawler_number.times do
+        @threads << Thread.new do
+          crawler = Cralwer.new(css: '.entry-title > a')
+          urls = crawler.crawl(@queue.pop)
+          urls.each{ |url| @queue << url }
+        end
+      end
+      @threads.each(&:join)
+    end
+  end
+end

data/lib/tjcrawler/version.rb

@@ -0,0 +1,3 @@
+module Tjcrawler
+  VERSION = "0.0.1"
+end

data/spec/crawler_spec.rb

@@ -0,0 +1,10 @@
+require 'spec_helper'
+require 'tjcrawler/crawler'
+
+describe Tjcrawler::Crawler do
+  it '#crawl' do
+    crawler = Tjcrawler::Crawler.new(css: '.entry-title > a')
+    result = crawler.crawl('http://tonytonyjan.net/blog/', '.entry-title > a')
+    expect(result.urls).to eql ["http://tonytonyjan.net/2015/01/03/2014-review/", "http://tonytonyjan.net/2014/12/20/intorduction-to-rails-4-dot-2/", "http://tonytonyjan.net/2014/10/10/rubykaigi-2014-feedback/", "http://tonytonyjan.net/2014/10/07/multi-line-c-macros/", "http://tonytonyjan.net/2014/06/28/fcfc-movie-downloader/", "http://tonytonyjan.net/2014/06/27/fb-page-countdown/", "http://tonytonyjan.net/2014/06/26/sfacg-comic-downloader/", "http://tonytonyjan.net/2014/06/20/swift-optional-chaining-on-ruby/", "http://tonytonyjan.net/2014/06/14/use-plurk-api-to-make-a-robot/", "http://tonytonyjan.net/2014/05/30/5xruby-start/"]
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,2 @@
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+require 'tjcrawler'

data/spec/tjcrawler_spec.rb

@@ -0,0 +1,7 @@
+require 'spec_helper'
+
+describe Tjcrawler do
+  it 'has a version number' do
+    expect(Tjcrawler::VERSION).not_to be nil
+  end
+end

data/tjcrawler.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'tjcrawler/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "tjcrawler"
+  spec.version       = Tjcrawler::VERSION
+  spec.authors       = ["Jian Weihang"]
+  spec.email         = ["tonytonyjan@gmail.com"]
+  spec.summary       = %q{Simple crawling tool.}
+  spec.description   = %q{Simple crawling tool.}
+  spec.homepage      = ""
+  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_dependency 'nokogiri'
+  spec.add_dependency 'activerecord'
+  spec.add_dependency 'activesupport'
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec"
+end

metadata

@@ -0,0 +1,155 @@
+--- !ruby/object:Gem::Specification
+name: tjcrawler
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Jian Weihang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-01-11 00:00:00.000000000 Z
+dependencies:
+- !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: activerecord
+  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: activesupport
+  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: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !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: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Simple crawling tool.
+email:
+- tonytonyjan@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- examples/dsl.rb
+- examples/dsl_parser.rb
+- examples/fc2.rb
+- examples/fc2_parse.rb
+- examples/schema.rb
+- lib/tjcrawler.rb
+- lib/tjcrawler/config.rb
+- lib/tjcrawler/crawler.rb
+- lib/tjcrawler/crawler/result.rb
+- lib/tjcrawler/page.rb
+- lib/tjcrawler/parser.rb
+- lib/tjcrawler/scheduler.rb
+- lib/tjcrawler/version.rb
+- spec/crawler_spec.rb
+- spec/spec_helper.rb
+- spec/tjcrawler_spec.rb
+- tjcrawler.gemspec
+homepage: ''
+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: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Simple crawling tool.
+test_files:
+- spec/crawler_spec.rb
+- spec/spec_helper.rb
+- spec/tjcrawler_spec.rb