fly_parser 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 220a36cf7e2845300835a2f2aa9c931e01245402
-  data.tar.gz: 7bbcbb1959f8d78d690223265ce95b0418f5116e
+  metadata.gz: a4b60890098babea5cdf0a19b2ab7f72207bce93
+  data.tar.gz: a5cf7fdba982c30f622f2c048ea5ef08d6a4565a
 SHA512:
-  metadata.gz: 3e33cb8372a87e60b830c91343bbcd05705300644c073f5094adf8017686f8d59a874e2a10d8672795c07823c5eeeb1695c184c52ac8fe2e99081eb21a8f74d1
-  data.tar.gz: f398560cf2541d717de50ba5158996a0bb5bbb53b19fc443ee2d0283b41417cb873200acb4fd83bbf2e71847f6535bb12eb225dee86129fb18d2a01ad3a8107f
+  metadata.gz: 4d9bfcfbc33a83acbf053cca55206f27377a1f6ab62ead285def08fc43ef659ea61aee533c5c743b21ee06b8d7c22e79b77942370ce76ace69270e14f359f5fd
+  data.tar.gz: f4b199bf649c121cbf1883e00acf451742dd25830076bc3b55a62258e149d1c314026e447580a3c8e2eab3d42b6648e5b9adeb763056aa3bec10322c62d6c288

data/lib/fly_parser/sources/news-nl.rb

@@ -0,0 +1,30 @@
+module Parser
+  class NewsNl < XmlBase
+    def initialize(source, options = {})
+      super
+    end
+
+    def parse_all
+      items = @source.search('//item')
+      # last_date = Time.now - 2.years # for dev 2 years
+      # select! or reject! is not exists for Nokogiri#NodeSet
+      # items = items.select {|item| item.xpath('pubDate').first.content() > last_date }
+      items.map do |item|
+        title = item.xpath('title/text()').text()
+        date = item.xpath('pubDate').first.content()
+        link = item.xpath('link/text()').text()
+        page = Nokogiri::HTML(open(link))
+
+        next if page.search('#article-image a img').first.nil?
+        poster_image = page.search('#article-image a img').first.attributes['src'].value
+        full_desc = item.xpath('description/text()')
+        # remove href attributes
+        full_desc = full_desc.text().gsub(/<a href="([a-zA-Z:\/\.\d\-]*)">(.*)<\/a>/,'<a>\2</a>')
+
+        copyright = "<p>Source: <a href='#{@copyright[:url]}'>#{@copyright[:title]}</a></p>"
+        content = full_desc + copyright
+        {title: title, content: content, poster_image: poster_image}
+      end.compact
+    end
+  end
+end

data/lib/fly_parser/sources/news.rb

@@ -1,28 +1,7 @@
 module Parser
-  class News
+  class News < XmlBase
     def initialize(source, options = {})
-      if options[:type] == :file
-        source = fake_url(source)
-      end
-      @copyright = copyright(options)
-      @source = Parser.connect(source)
-      @delay ||= 10
-    end
-
-    def fake_url(source)
-      stream = File.read(source)
-      # test_file.com is a random url, just for Mechanize parsing
-      url = "http://www.google.com"
-      FakeWeb.register_uri(:get, url, :body => stream, :content_type => "application/xml")
-      url
-    end
-
-    def copyright(options)
-      source = options[:source]
-      {
-        url: source['copyright'],
-        title: source['copyright_title']
-      }
+      super
     end
 
     def parse_all

data/lib/fly_parser/xml_base.rb

@@ -0,0 +1,28 @@
+module Parser
+  class XmlBase
+    def initialize(source, options = {})
+      if options[:type] == :file
+        source = fake_url(source)
+      end
+      @copyright = copyright(options)
+      @source = Parser.connect(source)
+      @delay ||= 10
+    end
+
+    def fake_url(source)
+      stream = File.read(source)
+      # test_file.com is a random url, just for Mechanize parsing
+      url = "http://www.google.com"
+      FakeWeb.register_uri(:get, url, :body => stream, :content_type => "application/xml")
+      url
+    end
+
+    def copyright(options)
+      source = options[:source]
+      {
+        url: source['copyright'],
+        title: source['copyright_title']
+      }
+    end
+  end
+end

data/lib/fly_parser.rb

@@ -5,9 +5,8 @@ require 'pry'
 require 'open-uri'
 require 'yaml'
 require 'mechanize'
-BASE_PATH = File.expand_path("fly_parser/base", File.dirname(__FILE__))
+BASE_PATH = File.expand_path("fly_parser/*.rb", File.dirname(__FILE__))
 LOGO_PATH = File.expand_path("fly_parser/logo.txt", File.dirname(__FILE__))
-MECHANIZE_FIX = File.expand_path("fly_parser/mechanize_fix", File.dirname(__FILE__))
 
 Pry.config.print = proc { |output, value| output.puts value.ai }
 
@@ -24,17 +23,15 @@ def require_all(path)
 end
 
 unless defined? Rails
-  require BASE_PATH
+  Dir[BASE_PATH].each do |base_file|
+    require base_file
+  end
   Dir.chdir RAILS_ROOT
   require RAILS_BOOT_PATH
   require RAILS_CONFIG_PATH
   require_all 'fly_parser/sources'
 end
 
-# fix mechanize by monkey-patching :)
-require MECHANIZE_FIX
-
-
 module Parser
   class << self
     # Get HTTP Source
@@ -114,6 +111,10 @@ module Parser
             item["parser"] = Parser::News.new(item["file"], {type: :file, source: source})
           end
         end
+      when "news-nl"
+        source["items"].each do |item|
+          item["parser"] = Parser::NewsNl.new(item["url"], source: source)
+        end
       end
     end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fly_parser
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Ruslan Korolev
@@ -123,8 +123,10 @@ files:
 - lib/fly_parser/sources/astrology.rb
 - lib/fly_parser/sources/exercise.rb
 - lib/fly_parser/sources/fitness.rb
+- lib/fly_parser/sources/news-nl.rb
 - lib/fly_parser/sources/news.rb
 - lib/fly_parser/sources/sport.rb
+- lib/fly_parser/xml_base.rb
 homepage: http://rubygems.org
 licenses:
 - MIT