taiwanese_news_parser 0.0.1

data/spec/taiwanese_news_parser/parser/udn_spec.rb

@@ -0,0 +1,42 @@
+require 'spec_helper'
+
+describe TaiwaneseNewsParser::Parser::Udn do
+  describe '#parse' do
+    it do
+      url = 'http://udn.com/NEWS/NATIONAL/NAT4/7996060.shtml'
+      FakeWeb.register_uri(:get, url, body:sample(__FILE__,'udn_s1.html'))
+      article = described_class.new(url).parse
+      article[:title].should == '國光免費去宜蘭第二天 零星衝突'
+      article[:content].should include('國光客運新開北宜高國5三條新路線，今天開放免費試乘第二天')
+      article[:company_name].should == '聯合晚報'
+      article[:reporter_name].should == '邱瓊平'
+      article[:published_at].should == Time.new(2013,6,29,16,17)
+    end
+  end
+  describe '#parse_reporter_name' do
+    it do
+      subject = described_class.new('http://udn.com/NEWS/NATIONAL/NAT2/8040540.shtml')
+      subject.stub(:get_company_name_and_reporter_name){'中央社╱桃園20日電'}
+
+      expect{ subject.parse_reporter_name }.to_not raise_error
+    end
+  end
+  describe '#reproduced?' do
+    it do
+      subject = described_class.new('http://udn.com/NEWS/NATIONAL/NAT2/8040540.shtml')
+      subject.stub(:get_company_name_and_reporter_name){'中央社╱桃園20日電'}
+      subject.reproduced?.should == true
+    end
+  end
+  describe '#parse_url_id' do
+    it do
+      url = 'http://udn.com/news/national/nats4/8099187.shtml'
+      described_class.parse_url_id(url).should == '8099187'
+    end
+    it 'breaking news' do
+      url = 'http://udn.com/NEWS/BREAKINGNEWS/BREAKINGNEWS1/8101247.shtml'
+      described_class.parse_url_id(url).should == '8101247'
+    end
+  end
+end
+

data/taiwanese_news_parser.gemspec

@@ -0,0 +1,30 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'taiwanese_news_parser/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "taiwanese_news_parser"
+  spec.version       = TaiwaneseNewsParser::VERSION
+  spec.authors       = ["lulalala"]
+  spec.email         = ["mark@goodlife.tw"]
+  spec.description   = %q{台灣各新聞網站新聞解析器}
+  spec.summary       = %q{Parser for various news agency websites in Taiwan}
+  spec.homepage      = "https://github.com/lulalala/taiwanese_news_parser"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  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_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec", "~> 2.6"
+  spec.add_development_dependency "fakeweb", "~> 1.3"
+  spec.add_development_dependency "timecop", "~> 0.6.1"
+
+  spec.add_dependency 'addressable', '~> 2.0'
+  spec.add_dependency 'nokogiri', '~> 1.5'
+  spec.add_dependency 'memoist', '~> 0.9'
+end

metadata

@@ -0,0 +1,237 @@
+--- !ruby/object:Gem::Specification
+name: taiwanese_news_parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- lulalala
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-03-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  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: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: fakeweb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: timecop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.6.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.6.1
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: memoist
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.9'
+description: 台灣各新聞網站新聞解析器
+email:
+- mark@goodlife.tw
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- g0v.json
+- lib/taiwanese_news_parser.rb
+- lib/taiwanese_news_parser/parser.rb
+- lib/taiwanese_news_parser/parser/apple_daily.rb
+- lib/taiwanese_news_parser/parser/china_times.rb
+- lib/taiwanese_news_parser/parser/cna.rb
+- lib/taiwanese_news_parser/parser/cts.rb
+- lib/taiwanese_news_parser/parser/ettoday.rb
+- lib/taiwanese_news_parser/parser/liberty_times.rb
+- lib/taiwanese_news_parser/parser/liberty_times_big5.rb
+- lib/taiwanese_news_parser/parser/now_news.rb
+- lib/taiwanese_news_parser/parser/tvbs.rb
+- lib/taiwanese_news_parser/parser/udn.rb
+- lib/taiwanese_news_parser/url_cleaner.rb
+- lib/taiwanese_news_parser/version.rb
+- spec/spec_helper.rb
+- spec/taiwanese_news_parser/parser/apple_daily_s1.html
+- spec/taiwanese_news_parser/parser/apple_daily_s2.html
+- spec/taiwanese_news_parser/parser/apple_daily_s3.html
+- spec/taiwanese_news_parser/parser/apple_daily_spec.rb
+- spec/taiwanese_news_parser/parser/china_times_s1.html
+- spec/taiwanese_news_parser/parser/china_times_s2.html
+- spec/taiwanese_news_parser/parser/china_times_s3.html
+- spec/taiwanese_news_parser/parser/china_times_s4.html
+- spec/taiwanese_news_parser/parser/china_times_spec.rb
+- spec/taiwanese_news_parser/parser/cna_s1.html
+- spec/taiwanese_news_parser/parser/cna_spec.rb
+- spec/taiwanese_news_parser/parser/cts_s1.html
+- spec/taiwanese_news_parser/parser/cts_s2.html
+- spec/taiwanese_news_parser/parser/cts_spec.rb
+- spec/taiwanese_news_parser/parser/ettoday_s1.html
+- spec/taiwanese_news_parser/parser/ettoday_s2.html
+- spec/taiwanese_news_parser/parser/ettoday_spec.rb
+- spec/taiwanese_news_parser/parser/liberty_times_big5_s1.html
+- spec/taiwanese_news_parser/parser/liberty_times_big5_spec.rb
+- spec/taiwanese_news_parser/parser/liberty_times_s1.html
+- spec/taiwanese_news_parser/parser/liberty_times_spec.rb
+- spec/taiwanese_news_parser/parser/now_news_s1.html
+- spec/taiwanese_news_parser/parser/now_news_s2.html
+- spec/taiwanese_news_parser/parser/now_news_spec.rb
+- spec/taiwanese_news_parser/parser/tvbs_s1.html
+- spec/taiwanese_news_parser/parser/tvbs_s2.html
+- spec/taiwanese_news_parser/parser/tvbs_spec.rb
+- spec/taiwanese_news_parser/parser/udn_s1.html
+- spec/taiwanese_news_parser/parser/udn_spec.rb
+- taiwanese_news_parser.gemspec
+homepage: https://github.com/lulalala/taiwanese_news_parser
+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: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Parser for various news agency websites in Taiwan
+test_files:
+- spec/spec_helper.rb
+- spec/taiwanese_news_parser/parser/apple_daily_s1.html
+- spec/taiwanese_news_parser/parser/apple_daily_s2.html
+- spec/taiwanese_news_parser/parser/apple_daily_s3.html
+- spec/taiwanese_news_parser/parser/apple_daily_spec.rb
+- spec/taiwanese_news_parser/parser/china_times_s1.html
+- spec/taiwanese_news_parser/parser/china_times_s2.html
+- spec/taiwanese_news_parser/parser/china_times_s3.html
+- spec/taiwanese_news_parser/parser/china_times_s4.html
+- spec/taiwanese_news_parser/parser/china_times_spec.rb
+- spec/taiwanese_news_parser/parser/cna_s1.html
+- spec/taiwanese_news_parser/parser/cna_spec.rb
+- spec/taiwanese_news_parser/parser/cts_s1.html
+- spec/taiwanese_news_parser/parser/cts_s2.html
+- spec/taiwanese_news_parser/parser/cts_spec.rb
+- spec/taiwanese_news_parser/parser/ettoday_s1.html
+- spec/taiwanese_news_parser/parser/ettoday_s2.html
+- spec/taiwanese_news_parser/parser/ettoday_spec.rb
+- spec/taiwanese_news_parser/parser/liberty_times_big5_s1.html
+- spec/taiwanese_news_parser/parser/liberty_times_big5_spec.rb
+- spec/taiwanese_news_parser/parser/liberty_times_s1.html
+- spec/taiwanese_news_parser/parser/liberty_times_spec.rb
+- spec/taiwanese_news_parser/parser/now_news_s1.html
+- spec/taiwanese_news_parser/parser/now_news_s2.html
+- spec/taiwanese_news_parser/parser/now_news_spec.rb
+- spec/taiwanese_news_parser/parser/tvbs_s1.html
+- spec/taiwanese_news_parser/parser/tvbs_s2.html
+- spec/taiwanese_news_parser/parser/tvbs_spec.rb
+- spec/taiwanese_news_parser/parser/udn_s1.html
+- spec/taiwanese_news_parser/parser/udn_spec.rb