telegraph-parser 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c27c84d13c2d7725fbb32104dc5a42a92998ceb0
-  data.tar.gz: f42a5d5cc5a7c1135d615df81de818cbec4e85ea
+  metadata.gz: 26cc01f88e7399f22fa4289fbb7d48dd9abb1e42
+  data.tar.gz: 3396ed38a2844d8daf0512107246e2f9cb07fa37
 SHA512:
-  metadata.gz: 656239f075164f8d6dd4a241cc000d166ba1c9ad60071e905e979d2c1f9bc1914badf8d314146af878ba7d3f7a9a3ae8ebc29268a0d3301b5207dc2c8399f4e4
-  data.tar.gz: d62631df9d0482117e006283bb43adb40743dfccff430e5b7e8623f3a9dd4894f50b53685b1c8d8a1ca6822c255458333c4d59e58d232c28807cbf466615d06e
+  metadata.gz: 9275b8c5a759ab28c47dc4d0da3968ba965c9a5bcb8684dbbb7bac626013b348b6649597b57373958d5d9d3a52a59c4f62e1af5b6f2b19455cd16e6b18e0ebe0
+  data.tar.gz: 51ba6f30a59614dcd26670c101bd059b4a6f6655c985fc7b0eaa261c2350be350a5259caa75a29dcfd575d6e9fc7b53c2e272fcce7ede226a946f606486a94a8

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.2.3
+before_install: gem install bundler -v 1.11.2

data/lib/telegraph/parser/article.rb

@@ -1,21 +1,21 @@
 module Telegraph
   module Parser
     class Article
-      attr_accessor :id, :title, :author, :content, :images
+      ATTRIBUTES = %i[id title author content images].freeze
+
+      attr_reader *ATTRIBUTES
 
       def initialize(attributes)
         attributes.each do |attr, val|
-          next unless respond_to?("#{attr}=")
-          send("#{attr}=", val)
+          next unless ATTRIBUTES.include?(attr.to_sym)
+          instance_variable_set(:"@#{attr}", val)
         end
       end
 
-      def self.load(article_id, image_prefix: '')
-        binding = Binding.new(article_id)
-
-        Parser.new(binding, image_prefix).article.tap do |article|
-          article.id = article_id
-        end
+      def self.find(article_id, image_prefix: '')
+        parser = Parser.new(article_id, image_prefix)
+        parser.fetch_and_parse!
+        Article.new(parser.parsed_data)
       end
     end
   end

data/lib/telegraph/parser/errors.rb

@@ -0,0 +1,5 @@
+module Telegraph
+  module Parser
+    class ArticleNotFound < StandardError; end
+  end
+end

data/lib/telegraph/parser/fetcher.rb

@@ -0,0 +1,23 @@
+require 'open-uri'
+
+module Telegraph
+  module Parser
+    class Fetcher
+      HOST = 'telegra.ph'.freeze
+
+      def fetch(article_id)
+        Net::HTTP.get(HOST, "/#{article_id}")
+      rescue EOFError
+        raise Telegraph::Parser::ArticleNotFound
+      end
+
+      def fetch_image(src, prefix)
+        { image_id(src, prefix) => open(src).read }
+      end
+
+      def image_id(src, prefix)
+        "#{prefix}/#{File.basename(URI.parse(src).path)}"
+      end
+    end
+  end
+end

data/lib/telegraph/parser/parser.rb

@@ -3,48 +3,56 @@ require 'nokogiri'
 module Telegraph
   module Parser
     class Parser
-      attr_accessor :bindings, :page, :article, :image_prefix
+      attr_reader :parsed_data
 
-      def initialize(binding, image_prefix)
-        self.bindings = binding
-        self.image_prefix = image_prefix
-        parse_html
+      def initialize(article_id, image_prefix)
+        @fetcher = Fetcher.new
+        @article_id = article_id
+        @image_prefix = image_prefix
+      end
+
+      def fetch_and_parse!
+        load_page!
+        load_images!
+        compile_parsed_data!
       end
 
       private
 
-      def page
-        @page ||= Nokogiri::HTML(bindings.content).css('article')
+      def load_page!
+        @page = Nokogiri::HTML(@fetcher.fetch(@article_id)).css('article')
       end
 
-      def images
-        {}.tap do |images|
-          page.search('.//img').each do |image|
-            images.merge!(bindings.image(image.attributes['src'].value,
-                                         image_prefix))
-          end
-        end
+      def compile_parsed_data!
+        @parsed_data = {
+          article_id: @article_id,
+          title:      tag_content(:h1),
+          author:     tag_content(:address),
+          content:    without_tags,
+          images:     @images
+        }
       end
 
-      def parse_html
-        images_hash = images
-        self.article = Article.new(title: tag_content(:h1),
-                                   author: tag_content(:address),
-                                   content: without_tags,
-                                   images: images_hash)
+      def load_images!
+        @images = {}
+
+        @page.search('.//img').each do |image|
+          i = @fetcher.fetch_image(image.attributes['src'].value, @image_prefix)
+          @images.merge!(i)
+        end
       end
 
       def tag_content(tag)
-        page.search(".//#{tag}").text
+        @page.search(".//#{tag}").text
       end
 
       def without_tags
-        page_copy = page.dup
-        %i(h1 address).each { |tag| page.search(".//#{tag}").remove }
+        page_copy = @page.dup
+        %i(h1 address).each { |tag| @page.search(".//#{tag}").remove }
 
         page_copy.search('.//img').each do |image|
           image.attributes['src'].value =
-            bindings.image_id(image.attributes['src'].value, image_prefix)
+            @fetcher.image_id(image.attributes['src'].value, @image_prefix)
         end
 
         page_copy.remove_attr('id').remove_class.to_s

data/lib/telegraph/parser/version.rb

@@ -1,5 +1,5 @@
 module Telegraph
   module Parser
-    VERSION = "0.0.1"
+    VERSION = "0.0.2"
   end
 end

data/lib/telegraph/parser.rb

@@ -1,5 +1,6 @@
 require "telegraph/parser/version"
-require "telegraph/parser/binding"
+require "telegraph/parser/errors"
+require "telegraph/parser/fetcher"
 require "telegraph/parser/parser"
 require "telegraph/parser/article"
 

data/telegraph-parser.gemspec

@@ -22,4 +22,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.0"
   spec.add_development_dependency "nokogiri", "~> 1.6.8"
+  spec.add_development_dependency "pry"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: telegraph-parser
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Sergey Vernidub
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-12-11 00:00:00.000000000 Z
+date: 2018-06-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -66,6 +66,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.6.8
+- !ruby/object:Gem::Dependency
+  name: pry
+  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: 
 email:
 - svernidub@gmail.com
@@ -74,6 +88,8 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".rspec"
+- ".travis.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -82,7 +98,8 @@ files:
 - bin/setup
 - lib/telegraph/parser.rb
 - lib/telegraph/parser/article.rb
-- lib/telegraph/parser/binding.rb
+- lib/telegraph/parser/errors.rb
+- lib/telegraph/parser/fetcher.rb
 - lib/telegraph/parser/parser.rb
 - lib/telegraph/parser/version.rb
 - telegraph-parser.gemspec

data/lib/telegraph/parser/binding.rb

@@ -1,31 +0,0 @@
-require 'open-uri'
-
-module Telegraph
-  module Parser
-    class Binding
-      BASE_URI = 'telegra.ph'
-
-      attr_accessor :article_id
-
-      def initialize(article_id)
-        self.article_id = article_id
-      end
-
-      def content
-        Net::HTTP.get(BASE_URI, "/#{article_id}")
-      rescue EOFError
-        ""
-      end
-
-      def image(src, prefix)
-        src.gsub!('http://telegra.ph', '')
-        { image_id(src, prefix) => open("http://#{BASE_URI}#{src}").read }
-      end
-
-      def image_id(src, prefix)
-        src.gsub!('http://telegra.ph', '')
-        "#{prefix}/#{File.basename(URI.parse("#{BASE_URI}#{src}").path)}"
-      end
-    end
-  end
-end