murmuring_spider 0.0.2

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,3 @@
+rvm:
+  - 1.8.7 # (current default)
+  - 1.9.2

data/Gemfile

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

data/Guardfile

@@ -0,0 +1,9 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec', :version => 2 do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+end
+

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 tomykaira
+
+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 +1,40 @@
+# MurmuringSpider
+
+[![Build Status](https://secure.travis-ci.org/tomykaira/murmuring_spider.png)](http://travis-ci.org/tomykaira/murmuring_spider)
+
+
+MurmuringSpider is a concise Twitter crawler.
+
+When we write a data-mining / text-mining application based on twitter's timeline, we have to collect and store tweets first.
+
+I am irritated with writing such crawler repeatedly, so I wrote this.
+
+What you have to do is only to add query and to run them periodically.
+
+Thanks to consistent Twitter API and [twitter gem](http://twitter.rubyforge.org/), it is quite easy to track various types of timelines (such as user_timeline, home_timeline, search...)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'murmuring_spider'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install murmuring_spider
+
+## Usage
+
+[Usage of murmuring spider — Gist](https://gist.github.com/2060445)
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,14 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"
+
+begin
+  require 'rspec/core'
+  require 'rspec/core/rake_task'
+  RSpec::Core::RakeTask.new(:spec) do |spec|
+    spec.pattern = FileList['spec/**/*_spec.rb']
+  end
+
+  task :default => :spec
+rescue LoadError
+  puts 'RSpec is not installed'
+end

data/lib/murmuring_spider.rb

@@ -0,0 +1,15 @@
+require 'dm-core'
+require 'dm-migrations'
+
+require "murmuring_spider/version"
+require "murmuring_spider/operation"
+require "murmuring_spider/status"
+
+module MurmuringSpider
+  extend MurmuringSpider
+
+  def database_init(db)
+    DataMapper.setup(:default, db)
+    DataMapper.auto_upgrade!
+  end
+end

data/lib/murmuring_spider/operation.rb

@@ -0,0 +1,82 @@
+require 'dm-core'
+require 'dm-validations'
+require 'twitter'
+
+#
+# Operation: represents request to Twitter
+#
+module MurmuringSpider
+  class Operation
+    include DataMapper::Resource
+
+    property :id, Serial
+    property :type, String
+    property :target, String
+    property :opts, Object
+
+    validates_uniqueness_of :target, :scope => :type
+
+    has n, :statuses
+
+    self.raise_on_save_failure = true
+
+    class << self
+      #
+      # Add an operation
+      # * _type_ : request type.  Name of a Twitter's method
+      # * _target_ : First argument of the Twitter's method.  Usually, an user or a operation
+      # * _opts_ : options. Second argument of the Twitter's method.
+      #
+      # returns : created Operation instance
+      #
+      # raises : DataMapper::SaveFailureError
+      #
+      def add(type, target, opts = {})
+        create(:type => type, :target => target, :opts => opts)
+      end
+
+      #
+      # Run all queries
+      #
+      def run_all(client = Twitter)
+        all.map { |o| o.run(client) }
+      end
+
+      #
+      # Remove an operation specified by type and target
+      #
+      def remove(type, target)
+        first(:type => type, :target => target).destroy
+      end
+    end
+
+    #
+    # Execute Twitter request and update :since_id of _opts_
+    # This method has side effect
+    #
+    # returns : Array of Twitter::Status
+    #
+    def collect_statuses(client = Twitter)
+      res = client.__send__(type, target, opts)
+      unless res.empty?
+        self.opts = opts.merge(:since_id => res.first.id)
+        save
+      end
+      res
+    end
+
+    #
+    # Collect tweet statuses and save them
+    # Return value should not be used
+    #
+    def run(client = Twitter)
+      collect_statuses(client).each do |s|
+
+        # not to raise error on save, remove an invalid status beforehand
+        last = self.statuses.new(s)
+        self.statuses.pop unless last.valid?
+      end
+      save
+    end
+  end
+end

data/lib/murmuring_spider/status.rb

@@ -0,0 +1,68 @@
+require 'dm-core'
+require 'twitter/status'
+
+class Twitter::Status
+  def url_expanded_text
+    if @attrs['entities'].nil?
+      text
+    else
+      @url_expanded_text ||= Array(@attrs['entities']['urls']).reduce(text) do |t, url|
+        t.gsub(url['url'], url['expanded_url'])
+      end
+    end
+  end
+end
+
+module MurmuringSpider
+  class Status
+    include DataMapper::Resource
+    property :id, Serial
+    property :tweet_id, String, :unique => :operation_id
+    property :text, String, :length => 255
+    property :user_id, String
+    property :screen_name, String
+    property :created_at, DateTime
+    property :extended, Object
+
+    belongs_to :operation
+
+    @@extended_fields = {}
+
+    class << self
+
+      #
+      # extend fields
+      # You can save a parameter of status which is not supported by default
+      # If block given, initializer gives the _Twitter::Status_ object to it,
+      # and the result of the given block is used as the field value
+      #
+      # * _field_ : field name. String or Symbol is expected.
+      #   _Twitter::Status_ should have the same name method.
+      # * _&b_ : block to get the field value from _Twitter::Status_ object.
+      #
+      def extend(field, &b)
+        @@extended_fields[field] = b
+        define_method(field.to_s) do
+          extended[field]
+        end
+      end
+    end
+
+    def initialize(s)
+      values = {}
+      @@extended_fields.each do |field, func|
+        if func
+          values[field] = func.call(s)
+        else
+          values[field] = s.__send__(field)
+        end
+      end
+      super(:tweet_id => s.id,
+          :text => s.url_expanded_text,
+          :user_id => s.user ? s.user.id : s.from_user_id,
+          :screen_name => s.user ? s.user.screen_name : s.from_user,
+          :created_at => s.created_at,
+          :extended => values)
+    end
+  end
+end

data/lib/murmuring_spider/version.rb

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

data/murmuring_spider.gemspec

@@ -0,0 +1,37 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/murmuring_spider/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["tomykaira"]
+  gem.email         = ["tomykaira@gmail.com"]
+  gem.description   = %q{MurmuringSpider is a concise Twitter crawler.
+
+When we write a data-mining / text-mining application based on twitter timeline, we have to collect and store tweets first.
+
+I am irritated with writing such crawler repeatedly, so I wrote this.
+
+What you have to do is only to add query and to run them periodically.
+
+Thanks to consistent Twitter API and twitter gem (http://twitter.rubyforge.org/), it is quite easy to track various types of timelines (such as user_timeline, home_timeline, search...)}
+  gem.summary       = %q{MurmuringSpider is a concise Twitter crawler with DataMapper.}
+  gem.homepage      = "https://github.com/tomykaira/murmuring_spider"
+
+  gem.add_dependency('dm-core')
+  gem.add_dependency('dm-migrations')
+  gem.add_dependency('dm-validations')
+  gem.add_dependency('twitter')
+
+  gem.add_development_dependency('rspec')
+  gem.add_development_dependency('guard')
+  gem.add_development_dependency('guard-rspec')
+  gem.add_development_dependency('database_cleaner')
+  gem.add_development_dependency('dm-sqlite-adapter')
+  gem.add_development_dependency('rake')
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "murmuring_spider"
+  gem.require_paths = ["lib"]
+  gem.version       = MurmuringSpider::VERSION
+end

data/spec/murmuring_spider/operation_spec.rb

@@ -0,0 +1,118 @@
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+
+describe MurmuringSpider::Operation do
+  let(:operation) { MurmuringSpider::Operation.add(:user_timeline, 'fake-user') }
+
+  subject { MurmuringSpider::Operation }
+  describe 'add' do
+    context 'when an user_timeline operation is added' do
+      before { subject.add(:user_timeline, 'tomy_kaira') }
+      it { should have(1).item }
+    end
+
+    context 'when the same operation is added' do
+      before { subject.add(:user_timeline, 'tomy_kaira') }
+      it "should raise error" do
+        expect { subject.add(:user_timeline, 'tomy_kaira') }.to raise_error(DataMapper::SaveFailureError)
+      end
+    end
+
+    context 'when an operation with different types and the same target is added' do
+      before { subject.add(:user_timeline, 'tomy_kaira') }
+      it "should create new operation" do
+        subject.add(:search, 'tomy_kaira')
+        subject.count.should == 2
+      end
+    end
+  end
+
+  describe 'run_all' do
+    before do
+      subject.add(:user_timeline, 'fake-user')
+      subject.add(:favorite, 'fake-user2')
+
+      Twitter.should_receive(:user_timeline).with('fake-user', anything).and_return([])
+      Twitter.should_receive(:favorite).with('fake-user2', anything).and_return([])
+    end
+
+    it "should run all tasks" do
+      subject.run_all
+    end
+  end
+
+  describe 'remove' do
+    before do
+      operation.should_not be_nil
+    end
+
+    it "should remove the operation" do
+      subject.remove(:user_timeline, 'fake-user')
+      subject.get(operation.id).should be_nil
+    end
+  end
+
+  describe 'collect_statuses' do
+    let(:response) { [status_mock(:id => 10), status_mock(:id => 7)] }
+    before { twitter_expectation }
+
+    context 'when the request succeeds' do
+      subject { operation.collect_statuses }
+      it { should == response }
+    end
+
+    context 'when requested twice' do
+      before do
+        twitter_expectation({:since_id => 10}, [])
+        operation.collect_statuses.should == response
+      end
+
+      subject { MurmuringSpider::Operation.get(operation.id).collect_statuses }
+      it { should be_empty }
+    end
+  end
+
+  context 'when an instance of Twitter::Client is given' do
+    let(:client) { mock(Twitter::Client) }
+    it "should use the instance, not Twitter module" do
+      client.should_receive(:user_timeline).with('fake-user', anything).and_return([])
+      operation.collect_statuses(client).should == []
+    end
+  end
+
+  describe 'run' do
+    let(:user) { mock(Twitter::User, :id => 12345, :screen_name => 'fake-user', :name => 'fake user') }
+    let(:status) { double(:id => 10,
+                   :user => user,
+                   :text => 'test tweet',
+                   :created_at => "Fri Mar 16 09:04:34 +0000 2012").as_null_object }
+    before { twitter_expectation({}, [status]) }
+
+    it 'should create Status instance' do
+      operation.run
+      MurmuringSpider::Status.should have(1).item
+      status = MurmuringSpider::Status.first(:tweet_id => 10)
+      status.should_not be_nil
+      status.operation.id.should == operation.id
+    end
+
+    context 'when the same tweet is returned by API twice' do
+      before do
+        operation.run
+        Twitter.should_receive(:user_timeline).and_return([status])
+        operation.run
+      end
+
+      it 'should create only one instance' do
+        MurmuringSpider::Status.should have(1).item
+      end
+    end
+  end
+
+  def status_mock(opts = {})
+    mock(Twitter::Status, opts)
+  end
+
+  def twitter_expectation(opts = {}, resp = response)
+    Twitter.should_receive(:user_timeline).with('fake-user', opts).and_return(resp)
+  end
+end

data/spec/murmuring_spider/status_spec.rb

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+
+shared_examples_for 'my tweet object' do
+  its(:tweet_id) { should == '180864326289207297' }
+  its(:text) { should == "OCaml でなにか書く課題がほしいです。プロコン的問題はのぞく" }
+  its(:user_id) { should == '287606751' }
+  its(:screen_name) { should == 'tomy_kaira' }
+  its(:created_at) { should == DateTime.parse("Sat Mar 17 03:53:10 +0000 2012") }
+end
+
+describe MurmuringSpider::Status do
+  let(:twitter_status) { Marshal.load(File.read(File.dirname(__FILE__) + '/../' + filename)) }
+  subject { MurmuringSpider::Status.new(twitter_status) }
+
+  context 'from user_timeline result' do
+    let(:filename) { 'twitter_status.dump' }
+    it_should_behave_like 'my tweet object'
+  end
+
+  context 'from search result' do
+    let(:filename) { 'twitter_search_status.dump' }
+    it_should_behave_like 'my tweet object'
+  end
+
+  context 'when the user extend the field' do
+    let(:filename) { 'twitter_status.dump' }
+    before do
+      MurmuringSpider::Status.extend(:source)
+    end
+    it_should_behave_like 'my tweet object'
+    its(:source) { should include 'web' }
+  end
+
+  context 'when the user extend the field with get strategy' do
+    before do
+      MurmuringSpider::Status.extend(:user_name) { |status| status.user ? status.user.name : status.from_user_name }
+    end
+
+    context 'with user_timeline result' do
+      let(:filename) { 'twitter_status.dump' }
+      its(:user_name) { should include 'といれ' }
+    end
+
+    context 'with search result' do
+      let(:filename) { 'twitter_search_status.dump' }
+      its(:user_name) { should include 'といれ' }
+    end
+  end
+
+  context 'when the tweet has shortened URL' do
+    let(:twitter_status) { Twitter::Status.new('text' => 'expansion test http://example.com/shortened', 'entities' => { 'urls' => [{"expanded_url"=>"http://www.example.com/expanded", "url"=>"http://example.com/shortened"}] }) }
+    subject { MurmuringSpider::Status.new(twitter_status) }
+    its(:text) { should ==  'expansion test http://www.example.com/expanded'}
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,30 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper.rb"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+
+require 'database_cleaner'
+require 'murmuring_spider'
+
+$LOAD_PATH.push File.expand_path(__FILE__ + '/../lib')
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  config.before(:suite) do
+    DatabaseCleaner.strategy = :truncation
+  end
+
+  config.before(:each) do
+    DatabaseCleaner.start
+  end
+
+  config.after(:each) do
+    DatabaseCleaner.clean
+  end
+end
+
+MurmuringSpider.database_init('sqlite3::memory:')

data/spec/twitter_search_status.dump

@@ -0,0 +1 @@
+o:Twitter::Status:@attrs{I"created_at:ETI"$Sat, 17 Mar 2012 03:53:10 +0000;TI"from_user;TI"tomy_kaira;TI"from_user_id;Ti߇$I"from_user_id_str;TI"287606751;TI"from_user_name;TI"といれ;TI"geo;T0I"id;Tl+	
0�%��I"id_str;TI"180864326289207297;TI"iso_language_code;TI"ja;TI"

metadata

@@ -0,0 +1,200 @@
+--- !ruby/object:Gem::Specification 
+name: murmuring_spider
+version: !ruby/object:Gem::Version 
+  prerelease: 
+  version: 0.0.2
+platform: ruby
+authors: 
+- tomykaira
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-04-13 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: dm-core
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  prerelease: false
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: dm-migrations
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  prerelease: false
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: dm-validations
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  prerelease: false
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: twitter
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  prerelease: false
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  name: guard
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id006
+- !ruby/object:Gem::Dependency 
+  name: guard-rspec
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id007
+- !ruby/object:Gem::Dependency 
+  name: database_cleaner
+  requirement: &id008 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id008
+- !ruby/object:Gem::Dependency 
+  name: dm-sqlite-adapter
+  requirement: &id009 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id009
+- !ruby/object:Gem::Dependency 
+  name: rake
+  requirement: &id010 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  prerelease: false
+  version_requirements: *id010
+description: |-
+  MurmuringSpider is a concise Twitter crawler.
+  
+  When we write a data-mining / text-mining application based on twitter timeline, we have to collect and store tweets first.
+  
+  I am irritated with writing such crawler repeatedly, so I wrote this.
+  
+  What you have to do is only to add query and to run them periodically.
+  
+  Thanks to consistent Twitter API and twitter gem (http://twitter.rubyforge.org/), it is quite easy to track various types of timelines (such as user_timeline, home_timeline, search...)
+email: 
+- tomykaira@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- .rspec
+- .travis.yml
+- Gemfile
+- Guardfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/murmuring_spider.rb
+- lib/murmuring_spider/operation.rb
+- lib/murmuring_spider/status.rb
+- lib/murmuring_spider/version.rb
+- murmuring_spider.gemspec
+- spec/murmuring_spider/operation_spec.rb
+- spec/murmuring_spider/status_spec.rb
+- spec/spec_helper.rb
+- spec/twitter_search_status.dump
+- spec/twitter_status.dump
+homepage: https://github.com/tomykaira/murmuring_spider
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: -814915267
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: -814915267
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.8.17
+signing_key: 
+specification_version: 3
+summary: MurmuringSpider is a concise Twitter crawler with DataMapper.
+test_files: 
+- spec/murmuring_spider/operation_spec.rb
+- spec/murmuring_spider/status_spec.rb
+- spec/spec_helper.rb
+- spec/twitter_search_status.dump
+- spec/twitter_status.dump