RSS to JSON converter

.gitignore

@@ -0,0 +1,4 @@
+*.json
+*.rss
+*.atom
+*.txt

lesson04/homework/Converter/README.md

@@ -0,0 +1,6 @@
+В данном репозитории находится конвертер из RSS формата в форматы ATOM, JSON и наоборот.
+
+Для использования программы используются следующие обязательные аттрибуты:  
+-i  --input=FILE 	//Входной файл  
+-o  --output=FORMAT 	//Выходной формат  
+

lesson04/homework/Converter/bin/optionParser.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+require 'optparse'
+
+class Parser
+@options = {}
+  def self.parse()
+  OptionParser.new do |parser|
+    parser.on('-i', '--input=FILE',
+              'File to convert')
+
+    parser.on('-o', '--output=FORMAT',
+              'Choose one of the formats: json, atom, rss')
+
+    parser.on('-h', '--help', 'Prints this help') do
+      puts parser
+      exit
+    end
+  end.parse!(into: @options)
+ @options
+end
+end

lesson04/homework/Converter/convert.rb

@@ -0,0 +1,13 @@
+require 'require_all'
+require '~/converter/main.rb'
+require 'nokogiri'
+require 'feedjira'
+require 'json'
+
+require_all 'lib'
+require_all 'bin'
+
+options = Parser.parse
+p options
+main = Main.new(options)
+main.run

lesson04/homework/Converter/lib/check/check.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Check
+  def self.valid_json?(json)
+    JSON.parse(json)
+    true
+  rescue JSON::ParserError => e
+    false
+  end
+
+  def self.check(data)
+    str = data.to_s
+    if str.include? '<feed'
+      'atom'
+    elsif str.include? '<rss'
+      'rss'
+    elsif valid_json?(str)
+      'json'
+    end
+  end
+end

lesson04/homework/Converter/lib/converters/convert_to_json.rb

@@ -0,0 +1,5 @@
+module ConvertToJson
+  def self.convert(data)
+     File.open('output.json', 'w+') { |f| f.write JSON.pretty_generate(data) }
+  end
+end

lesson04/homework/Converter/lib/parsers/atom_parser.rb

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+module ParseAtom
+  def self.parseFeed(doc)
+    parsedString = []
+    feed_title = doc.at_css('feed title').text.strip
+    feed_updated = doc.at_css('feed updated').text.strip
+    feed_author = doc.at_css('feed author name').text.strip
+    feed_id = doc.at_css('feed id').text.strip
+
+    parsedString.push(
+     title: feed_title,
+     link: feed_link,
+     updated: feed_updated,
+     author: feed_author,
+     id: feed_id
+    )
+  end
+
+  def self.parseEntry(doc)
+    items = []
+
+    doc.css('entry').each do |item|
+      entry_title = doc.at_css('entry title').text.strip
+      entry_id = doc.at_css('entry id') .text.strip
+      entry_updated = doc.at_css('entry updated').text.strip
+      entry_summary = doc.at_css('entry summary').text.strip
+
+      items.push(
+        title: entry_title,
+        id: entry_id,
+        updated: entry_updated,
+        summary: entry_summary
+      )
+
+    end
+
+    items
+  end
+
+  def self.parse(doc)
+    doc = Nokogiri::XML(doc)
+    result = { feed: parseFeed(doc),
+               entry: parseEntry(doc) }
+  end
+end

lesson04/homework/Converter/lib/parsers/json_parser.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+require 'json'
+
+module ParseJson
+  def self.parse(input)
+    data = JSON.parse(input)
+  end
+end

lesson04/homework/Converter/lib/parsers/rss_parser.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+
+module ParseRss
+  def self.parseFeed(doc)
+    parsedString = []
+    feed_image_content = {}
+    feed_language = doc.css('channel language').text.strip
+    feed_title = doc.at_css('channel title').text
+    feed_description = doc.at_css('channel description').text.strip
+    feed_link = doc.at_css('channel link').text.strip
+    feed_image_content = { 'url' => doc.css('channel image url').text.strip,
+                           'title' => doc.css('channel image title').text.strip,
+                           'link' => doc.css('channel image link').text.strip }
+
+    parsedString.push(
+      language: feed_language,
+      title: feed_title,
+      description: feed_description,
+      link: feed_link,
+      image: feed_image_content
+    )
+  end
+
+  def self.parseItems(doc)
+    items = []
+
+    item_tags = doc.xpath('//item/*').map(&:name).each.uniq
+    p item_tags
+    doc.css('item').each do |item|
+      parsed_strings = {}
+      attr_names = []
+      item_tags.each do |tag|
+        attr_hash = {}
+        if !doc.xpath("//item/#{tag}[@*]").empty? # if tag has attribute parse them
+          attr_names = doc.xpath("//item/#{tag}/@*").map(&:name).each.uniq
+          attr_names.each do |att|
+            attr_hash[att] = item.css(tag)[0][att]
+          end
+          parsed_strings[tag] = attr_hash
+        else
+          item_result = item.css(tag.to_s).text.strip
+          parsed_strings[tag] = item_result
+        end
+      end
+      items.push << parsed_strings
+    end
+    items
+  end
+
+  def self.parse(doc)
+    doc = Nokogiri::XML(doc)
+    result = { feed: parseFeed(doc),
+               items: parseItems(doc) }
+  end
+end

lesson04/homework/Converter/lib/readers/file_reader.rb

@@ -0,0 +1,6 @@
+module File_reader
+  def self.read(path)
+    file = File.open(path)
+    data = file.read
+  end
+end

lesson04/homework/Converter/lib/readers/link_reader.rb

@@ -0,0 +1,7 @@
+require 'open-uri'
+
+module Link_reader
+  def self.read(url)
+    data = open(url).read
+  end
+end

lesson04/homework/Converter/main.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+class Main
+  def initialize(options)
+    @input = options[:input]
+    @output_format = options[:output]
+    @sort = options[:sort]
+  end
+
+  def run
+    data = if @input.match('^https|http')
+             Link_reader.read(@input)
+           else
+             File_reader.read(@input)
+     end
+
+    parsed_data = if Check.check(data) == 'atom'
+                    ParseAtom.parse(data)
+                  elsif Check.check(data) == 'rss'
+                    ParseRss.parse(data)
+                  elsif Check.check(data) == 'json'
+                    ParseJson.parse(data)
+                  else
+                    p 'ERROR'
+                  end
+
+    if @output.to_s.downcase == 'atom'
+      ConvertToAtom.convert(parsed_data)
+    elsif @output.to_s.downcase == 'rss'
+      ConvertToRss.convert(parsed_data)
+    else
+      ConvertToJson.convert(parsed_data)
+    end
+  end
+end

lesson04/homework/converter/.gitignore

@@ -0,0 +1,6 @@
+*.json
+*.txt
+*.swp
+*.yml
+*.atom
+*.rss

lesson04/homework/converter/README.md

@@ -0,0 +1,10 @@
+В данном репозитории находится конвертер из RSS формата в форматы ATOM, JSON и наоборот.
+
+Для использования программы используются следующие обязательные аттрибуты:  
+-i  --input=FILE 	//Входной файл  
+-o  --output=FORMAT     //Выходной формат  
+
+Необязательный аттрибут для названия выходного файла:   
+-n  --name=FILE         //Имя выходного файла
+
+При отсутствии данного аттрибута, данные запишутся в файл output.txt

lesson04/homework/converter/bin/option_parser.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require 'optparse'
+
+# parse options
+class OptionParser
+  @options = {}
+  def self.parse
+    OptionParser.new do |parser|
+      parser.on('-i', '--input=FILE',
+                'File to convert')
+
+      parser.on('-o', '--output=FORMAT',
+                'Choose one of the formats: json, atom, rss')
+      parser.on('-n', '--name=FILE',
+                'Type converted file name')
+      parser.on('-h', '--help', 'Prints this help') do
+        exit
+      end
+    end.parse!(into: @options)
+    @options
+  end
+end

lesson04/homework/converter/convert.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require 'require_all'
+require '~/converter/main.rb'
+
+require_all 'lib'
+require_all 'bin'
+
+options = OptionParser.parse
+main = Main.new(options)
+main.run

lesson04/homework/converter/lib/check/check_format.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+# Check if input data matches one of the three formats: Atom, RSS, JSON
+module Check
+  def self.valid_json?(json)
+    JSON.parse(json)
+    true
+  rescue JSON::ParserError => e
+    false
+  end
+
+  def self.check(data)
+    str = data.to_s
+    if str.include? '<feed'
+      'atom'
+    elsif str.include? '<rss'
+      'rss'
+    elsif valid_json?(str)
+      'json'
+    else 'error'
+    end
+  end
+end

lesson04/homework/converter/lib/converters/base_converter.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module BaseConverter
+  def self.convert(data, option)
+    converters = ClassList.names('lib/converters/modules/*rb')
+    converters.each do |converter|
+      class_name = Module.const_get(converter)
+      # puts class_name.to_s.include?(option.capitalize)
+      if class_name.to_s.include?(option.capitalize)
+        return class_name.convert(data)
+      end
+    end
+  end
+end

lesson04/homework/converter/lib/converters/modules/convert_to_atom.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+
+# Class which converts hash data to RSS format
+module ConvertToAtom
+  def self.convert(data)
+    builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8') do |xml|
+      xml.atom('version' => '2.0', 'xmlns:atom' => 'http://www.w3.org/2005/Atom') do
+        data.values[0].each do |v|
+          xml.entry do
+            xml.title v[:title]
+            xml.summary v[:description]
+            xml.published v[:pubdate]
+          end
+        end
+      end
+    end
+    builder.to_xml
+  end
+end

lesson04/homework/converter/lib/converters/modules/convert_to_json.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require 'json'
+
+# Class which converts hash data to Json format
+module ConvertToJson
+  def self.convert(data)
+    JSON.pretty_generate(data)
+  end
+end

lesson04/homework/converter/lib/converters/modules/convert_to_rss.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+
+# Class which converts hash data to RSS format
+
+module ConvertToRss
+  def self.convert(data)
+    builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8') do |xml|
+      xml.rss('version' => '2.0', 'xmlns:atom' => 'http://www.w3.org/2005/Atom') do
+        data.values[0].each do |v|
+          xml.item do
+            xml.title       v[:title]
+            xml.description v[:description]
+            xml.pubDate     v[:pubdate]
+          end
+        end
+      end
+    end
+    builder.to_xml
+  end
+end