module Gnomika

Module containing all classes and functions of the application

Public Class Methods

fetch_category_info() click to toggle source

Gets information about all categories from the website @return An Array of Category objects

# File lib/gnomikologikon/web_processing.rb, line 13
def self.fetch_category_info
  response = HTTParty.get('https://www.gnomikologikon.gr/categ.php', {
    headers: {"User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"},
  })

  doc = Nokogiri::HTML.parse(response.body)
  # Each "big" category is stored in a table with class "authrst"
  category_tables = doc.xpath("//table[@class='authrst']")

  categories = []

  category_tables.each do |table|
    # Get category name. Category names are stored in td elements with class "authrsh"
    category_name = table.xpath("tr/td[@class='authrsh']").text

    # Get the subcategories of each category
    subcategories = []
    # Subcategories of each category are a elements in a list
    subcategory_elements = table.xpath("tr//ul//li//a")
    subcategory_elements.each do |element|
      subcategory_name = element.content
      # Need to prefix category URLs with the website URL
      subcategory_url = "https://www.gnomikologikon.gr/#{element[:href]}"
      subcategories << Subcategory.new(subcategory_name,subcategory_url)
    end

    categories << Category.new(category_name,subcategories: subcategories)
  end
  categories
end
get_quotes_for_categories(subcategories) { || ... } click to toggle source

Get all quotes for the given subcategories @yield Runs the given block after each subcategory is processed @param subcategories Array of subcategories @return Hash matching each subcategory to an Array of quotes

# File lib/gnomikologikon/web_processing.rb, line 49
def self.get_quotes_for_categories(subcategories)
  quotes = {}
  subcategories.each do |subcategory|
    response = HTTParty.get(subcategory.url, {
      headers: {"User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"},
    })
    quotes[subcategory] = get_quotes_from_html(response.body)
    yield if block_given?
    # Throttle the connection because processing is fast
    sleep 1
  end
  quotes
end
get_quotes_from_html(page_body) click to toggle source

Fetch all quotes from given HTML page @param page_body Body of HTML page to extract quotes from @return Array of quotes

# File lib/gnomikologikon/web_processing.rb, line 67
def self.get_quotes_from_html(page_body)
  doc = Nokogiri::HTML.parse(page_body)
  quotes_tables = doc.xpath("//table[@class='quotes']//td[@class='quote']")
  quotes = []
  quotes_tables.each do |quote|
    # Get quote contents
    content = quote.at_xpath("./text()").text
    # Check if there is an explanation
    explanation = quote.xpath("./table[@class='expth']//td")
    unless explanation.empty?
      # If an explanation exists, there are two td elements
      # Remove pavla
      explanation = explanation.reject{|element| element["class"] == "pavla"}
      # Keep the explanation td element
      explanation = explanation[0]
      content << "\n(#{explanation.text})"
    end
    # Check if there is a comment
    comment = quote.xpath("./p[contains(@class, 'comnt')]")
    unless comment.nil?
      # Do not add comment if it does not contain text
      content << "\n#{comment.text}" unless comment.text.empty?
    end
    # HTML p elements with class auth0-auth4 contain quote author and additional information (e.g. book)
    # Get the text of all auth p elements and combine them in a string
    author = quote.xpath(".//p[contains(@class, 'auth')]")
    author = author.map{|el| el.text}.join(' ')
    quotes << Quote.new(content,author)
  end
  quotes
end
main() click to toggle source
# File lib/gnomika.rb, line 12
def self.main
  # Parse command line arguments
  options = ArgParser.parse(ARGV)
  # Get available categories
  available_categories = Gnomika.fetch_category_info
  # Prompt user to select a category
  selected_category = select_category(available_categories)
  # Prompt user to select subcategories
  selected_subcategories = select_subcategories(selected_category)
  # Create a progress bar
  progressbar = ProgressBar.create(total: selected_subcategories.length, title: "Download Progress")
  # Get the quotes and display progress
  quotes =  Gnomika.get_quotes_for_categories(selected_subcategories){
    progressbar.increment
  }
  # Create quote files with the options given as parameters
  begin
    write_files(options, quotes)
  rescue StandardError => e
    STDERR.puts e.message
  end
end
select_category(categories) click to toggle source

Prompt the user to select a category @param categories Array of Category objects @return The Category object the user selected

# File lib/gnomikologikon/ui.rb, line 6
def self.select_category(categories)
  # Index starting from 1
  categories.each_with_index { |category, index| puts "#{index+1}. #{category.name}" }
  ok = false
  num = -1
  until ok
    print "Select a category: "
    STDOUT.flush
    input =  STDIN.gets
    begin
      # Remove 1 because display indexes starting from 1.
      num = Integer(input) - 1
      break unless num < 0 || num > categories.length-1
      # Input was number but out of bounds
      puts "Invalid selection!"
    rescue ArgumentError
      # Input could not be converted to integer
      puts "Invalid selection!"
    end
  end
  # Return Category object chosen by the user
  categories[num]
end
select_subcategories(category) click to toggle source

Prompt user to select subcategories. Selection can be a range e.g. 1-2, single categories e.g. 1,2,3 or both e.g 1,2-4 @param category The Category that will be shown @return Array of selected Subcategory objects

# File lib/gnomikologikon/ui.rb, line 35
def self.select_subcategories(category)
  subcategories = category.subcategories
  # Index starting from 1
  subcategories.each_with_index { |subcategory, index| puts "#{index+1}. #{subcategory.name}" }
  puts "You can select multiple categories separated by ',' or a range of categories with '-'."

  # Contains indexes of all subcategories specified by the user
  selected_indexes = []
  ok = false
  until ok
    print "Select subcategories: "
    # On each loop we assume input is ok until an error is encountered
    ok = true
    # Empty the indexes array, in case of leftovers from previous loop
    selected_indexes = []
    input = STDIN.gets
    # Split the input
    input = input.split(",")
    # Check each selection
    input.each do |selection|
      begin
        # We need to remove 1 from each because during selection category numbers started from 1
        selected_indexes += selection_to_array(selection, subcategories.length).map{|it| it - 1}
      rescue => error
        ok = false
        puts error.message
        break
      end
    end
  end
  # Remove any duplicate indexes
  selected_indexes.uniq!
  # Create an array with the corresponding Subcategory objects and return it
  selected_indexes.map { |index| subcategories[index]}
end
write_files(options, quotes) click to toggle source

Writes given quotes to files according to the given options. @param options GnomikaOptions object containing file output options @param quotes Hash matching each subcategory to an Array with quotes

# File lib/gnomikologikon/file_writer.rb, line 7
def self.write_files(options, quotes)
  # If no custom directory is specified, use the current directory
  output_directory = Dir.pwd
  if options.custom_output_dir_set
    custom_dir = options.custom_output_dir_value
    begin
      unless Dir.exist? custom_dir
        Dir.mkdir custom_dir
      end
      output_directory = custom_dir
    rescue StandardError => e
      raise e
    end
  end
  file_writer = FileWriter.new(output_directory, options.single_file, single_file_name: options.single_file_name)
  quotes.each_pair do |subcategory,subcategory_quotes|
    file_writer.write_quotes(subcategory.name,subcategory_quotes)
  end
  # Must generate strfiles for fortune command to work
  file_writer.generate_strfiles
end

Private Class Methods

selection_to_array(selection, max_available_index) click to toggle source

Converts given selection into an array of indexes. Throws an ArgumentError if the selection is invalid. An error message is included in the exception. This function must be used with a single selection (e.g 3 or 3-5), not with a list of many selections (e.g 1,2,3…) @param selection String of the selection @param max_available_index Used w @return Array of indexes included in the selection

# File lib/gnomikologikon/ui.rb, line 80
def self.selection_to_array(selection, max_available_index)
  # Check if selection is a range
  if selection.include?("-")
    # Try to process it as a range
    range_start, range_end = selection.split("-")
    begin
      range_start = Integer(range_start)
      range_end = Integer(range_end)
      # Check if range is correct. Start must be smaller or equal than end and end must be smaller or equal
      # to max_available index
      if range_start > range_end || range_end > max_available_index || range_start < 1
        raise ArgumentError
      end
      return (range_start..range_end).to_a
    rescue ArgumentError
      raise ArgumentError.new "Invalid range! (#{selection.strip})"
    end
  else
    # Assume selection is an integer
    begin
      number = Integer(selection)
      # Check limits
      if number < 1 || number > max_available_index
        raise ArgumentError
      end
      return [number]
    rescue
      raise ArgumentError.new "Invalid selection! (#{selection.strip})"
    end
  end
end