deadlist 1.0.1 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8cc3ef0661dbc9d67bc88bae8f63b3b42a273e3376647cfee377b9466c23c0d1
-  data.tar.gz: 5f2424f582c3c5c27f102cf842d64083c35b1d20e675e5513b1767014b064673
+  metadata.gz: edb67e52d7cf77e3a3f693fa49c5939be32fb714b247b67a5e7dfd4dc64d4b34
+  data.tar.gz: f9bfc50fd08fd7586f5c542e0c540e8c5ffafee8480af8e9b8dfc1d1d6be3c02
 SHA512:
-  metadata.gz: 5e1ca2667a3a681a0119da589919ed8486b416d7963eeb63a318605a4a0d0d1ad85d02b5c8b086587cbe92101992aedaf9fa6bb39a953ae864ddad32f154ad5a
-  data.tar.gz: 1f64dfee13234319fcbc450192d510e900add592839b32956950fa40c9c8e0cff1383edaec206fc5febaa88d4c1a265011cc089548f7e157265273a8e27097a2
+  metadata.gz: 76d8d658f14a546206b157a8765f48e1283f718e5c13864c0f7a605884f64e23235342f4767677b07a27e878cfc4cb00e96951fb5e85055efbcaafb69e3ea0dc
+  data.tar.gz: 48d2e2aead1b040a6034bfb946c7cb62048490c22796dfc9dfbcd4451822305758dd243c1ee3ad107c998697a16ce2155f29766f8aa5582354ba80948235d6f3

data/lib/deadlist/cli/argument_parser.rb

@@ -0,0 +1,54 @@
+class ArgumentParser
+  def self.parse(args, version)
+    params = {}
+    
+    parser = OptionParser.new do |opts|
+      opts.banner = "Usage: deadlist [options]"
+      opts.separator ""
+      opts.separator "Required options:"
+      
+      opts.on("-i", "--id ID", "ID of show to download") do |id|
+        params[:id] = id
+      end
+      
+      opts.on("-f", "--format FORMAT", "Format to download (mp3, flac, ogg)") do |format|
+        params[:format] = format.downcase
+      end
+      
+      opts.separator ""
+      opts.separator "Other options:"
+      
+      opts.on("-h", "--help", "Show this help") do
+        puts opts
+        exit
+      end
+      
+      opts.on("-v", "--version", "Show version") do
+        puts "deadlist v#{version}"
+        exit
+      end
+    end
+    
+    parser.parse!(args)
+    validate_required_params!(params, parser)
+    params
+  rescue OptionParser::InvalidOption => e
+    puts "Error: #{e.message}"
+    puts parser
+    exit(1)
+  end
+
+  private
+
+  def self.validate_required_params!(params, parser)
+    missing = []
+    missing << "--id" unless params[:id]
+    missing << "--format" unless params[:format]
+    
+    unless missing.empty?
+      puts "Error: Missing required arguments: #{missing.join(', ')}"
+      puts parser
+      exit(1)
+    end
+  end
+end

data/lib/deadlist/cli/client.rb

@@ -1,52 +1,29 @@
 # The Client class manages HTML scraping and parsing for the CLI and other classes above it. Any HTML work should be handled here.
 class Client
-    # Returns a show_data object for helping in the creation of a new Show
-    def scrape_show_info(show_link)
-        doc = get_page_source(show_link)
-        track_divs = doc.css('div[itemprop="track"]')
+    def query_show_info(show_id)
+        url = 'https://archive.org/metadata/' + show_id
+        response = HTTParty.get(url)
+
+        unless response.success?
+            raise "API request failed: #{response.code}"
+        end
+
+        unless response["metadata"]
+            raise "Invalid show ID: #{show_id}"
+        end
 
         show_data = {
-            date: extract_metadata(doc, itemprop: 'datePublished'),
-            location: extract_metadata(doc, label: 'Location'),
-            venue: extract_metadata(doc, label: 'Venue'),
-            transferred_by: extract_metadata(doc, label: 'Transferred by'),
-            duration: extract_metadata(doc, label: 'Run time'),
-            tracks: extract_track_data(track_divs)
+            date: response["metadata"]["date"],
+            location: response["metadata"]["coverage"],
+            venue: response["metadata"]["venue"],
+            transferred_by: response["metadata"]["transferer"],
+            duration: response["metadata"]["runtime"],
+            dir: response["metadata"]["identifier"],
+            files: response["files"]
         }
 
         return show_data
-    rescue => e
-        puts "\n❌ Data extraction failed: #{e.message}"
-    end
-
-    private 
-
-    # Returns nokogiri-fied page HTML for use in scraping show info
-    def get_page_source(show_link)
-        return Nokogiri::HTML(HTTParty.get(show_link).body)
-    rescue => e
-        puts "\n❌ Scraping failed: #{e.message}"
-    end
-
-    # Handles finding of values via 'label' and 'itemprop' Xpath values
-    def extract_metadata(doc, label: nil, itemprop: nil)
-        if label
-            # For dt/dd metadata pairs
-            doc.xpath("//dt[normalize-space(text())='#{label}']/following-sibling::dd").first&.text&.strip
-        elsif itemprop  
-            # For itemprop attributes
-            doc.xpath("//*[@itemprop='#{itemprop}']").first&.content&.strip
-        end
-    end
-
-    # Hunts through track-divs for data required to create Tracks
-    def extract_track_data(track_divs)
-        track_divs.each_with_index.map do |div, i|
-            {
-                pos: i + 1, 
-                name: div.css('meta[itemprop="name"]').first&.[]('content'),
-                links: div.css('link[itemprop="associatedMedia"]').map { |link| link['href'] }
-            }
-        end
+    rescue HTTParty::Error, StandardError => e
+        raise "Failed to fetch show data: #{e.message}"
     end
 end

data/lib/deadlist/cli/downloader.rb

@@ -1,17 +1,23 @@
 # A simple class to download files to a given directory. Expects details for the filename and a link.
 # One Downloader should be created / show being downloaded. Downloaders can run on seperate threads for getting many hows at once.
 class Downloader
+    BASE_API_URL = 'https://archive.org'
+
     def initialize(path, format)
         @path = path
         @format = format
     end
+  
+    def download_url_for_show(show_id)
+        "#{BASE_API_URL}/download/#{show_id}/"
+    end
 
     # Goes to a link (assuming the format is already validated), and gets the file, saving with argument names.
-    def get(pos, name, link)
-        uri = URI.parse(link); raise ArgumentError, "Only HTTP(S) URLs allowed" unless uri.is_a?(URI::HTTP)
-            
+    def get(root_url, track_object)
+        uri = URI.parse(root_url + track_object.filename); raise ArgumentError, "Only HTTP(S) URLs allowed" unless uri.is_a?(URI::HTTP)
         download = uri.open
-        filename = "#{@path}/#{pos} -- #{name}.#{@format}"
+        filename = "#{@path}/#{track_object.pos} -- #{track_object.title}.#{@format}"
+
         IO.copy_stream(download, filename)
     rescue => e
         puts "❌ Download failed: #{e.message}"

data/lib/deadlist/cli.rb

@@ -2,7 +2,9 @@ require_relative 'cli/client'
 require_relative 'cli/downloader'
 require_relative 'models/show'
 require_relative 'models/track'
+require_relative 'cli/argument_parser.rb'
 require 'fileutils'
+require 'optparse'
 
 # The CLI is the 'session' created by the main class, managing arguments passed in and housing methods for scraping and downloading shows.
 class CLI
@@ -15,34 +17,26 @@ class CLI
         parse_arguments(args)
     end
 
-    # Reads arguments passed at the command line and maps them to an instance object
-    def parse_arguments(args)
-        args.each do |arg|
-            key, value = arg.split('=')
-            @args[key.tr('--', '').to_sym] = value
-        end
-    end
-
     # Creates new show object with link given populated with metadata and track details
-    def scrape_links
-        @show = Show.new(@args[:show])
-        puts "\n💿 #{@show.tracks.length} tracks found!"
+    def create_show
+        extracted_id = extract_show_id(@args[:id])
+        @show = Show.new(extracted_id, @args[:format])
+
+        puts "\n💿 #{@show.name} - #{@show.tracks.length} tracks found!"
     rescue => e
         puts "\n❌ Scraping failed: #{e.message}"
     end
 
     # Validates format isn't for test, and passes directory + format arguments to the download method of a Show
     def download_show
-        download_format = @args[:format]
-
-        if download_format == "test"
-          puts "Test Download, skipping"
-        elsif @show.has_format?(download_format)
-            download_path = setup_directories(@show)
-            @show.download_tracks(download_path, download_format)
+        if @args[:format] == "test"
+          puts "Test Download, skipping"   
         else
-            puts "\n❌ #{download_format} not found for this show! #{@show.tracks[0].available_formats} available"
+            download_directory = setup_directories(@show)
+            @show.download_tracks(download_directory)
         end
+    rescue => e
+        puts "\n❌ Download failed: #{e.message}"
     end
 
     private
@@ -55,6 +49,19 @@ class CLI
         puts '='*52
     end
 
+    # Reads arguments passed at the command line and maps them to an instance object
+    def extract_show_id(show_input)
+        if show_input.include?('archive.org/details/')
+            show_input.split('/details/').last
+        else
+            show_input
+        end
+    end 
+    
+    def parse_arguments(args)
+        @args = ArgumentParser.parse(args, @version)
+    end
+
     # Configures directories that will be used by the downloader
     def setup_directories(show, base_path = Dir.pwd)
         # Create base shows directory
@@ -66,5 +73,7 @@ class CLI
         FileUtils.mkdir_p(show_dir)
 
         return show_dir
+    rescue => e
+        puts "\n❌ Directory creation failed: #{e.message}"
     end
 end

data/lib/deadlist/models/show.rb

@@ -2,35 +2,30 @@
 class Show
     attr_reader :name, :venue, :date, :location, :duration, :transferred_by, :tracks, :available_formats
 
-    def initialize(download_url)
-        @show_link = download_url
+    def initialize(show_id, format)
+        @show_id = show_id
+        @format = format
         @name = nil
         @date = nil
         @location = nil
         @venue = nil
         @duration = nil
         @transferred_by = nil
-        @available_formats = []
+        @url = nil
         @tracks = nil
 
         set_show_info
     end
 
-    # Returns whether or not a given format is available for this show
-    def has_format?(requested_format)
-      @tracks[0].has_format?(requested_format)
-    end
-
     # Initializes a Downloader and passes track details
-    def download_tracks(path, format)
-        dl = Downloader.new(path, format)
+    def download_tracks(path)
+        dl = Downloader.new(path, @format)
+        download_url = dl.download_url_for_show(@show_id)
 
         @tracks.each do |track|
-            track_link = track.url_for_format(format)
-
-            dl.get(track.pos, track.name, track_link)
+            dl.get(download_url, track)
 
-            puts "⚡️ #{track.pos} - #{track.name} downloaded successfully"
+            puts "⚡️ #{track.pos} - #{track.title} downloaded successfully"
         end
     end
 
@@ -38,21 +33,40 @@ class Show
 
     # On initialization, show variables are extracted from the HTML data scraped by the Client.
     def set_show_info
-        show_data = Client.new.scrape_show_info(@show_link)
-        
+        show_data = Client.new.query_show_info(@show_id)
+
         @date = show_data[:date]
         @location = show_data[:location]
         @venue = show_data[:venue]
         @duration = show_data[:duration]
         @transferred_by = show_data[:transferred_by]
         @name = "#{show_data[:date]} - #{show_data[:venue]} - #{show_data[:location]}"
-        @tracks = set_tracks(show_data[:tracks])
+        @tracks = set_tracks(show_data[:files])
+        @url = "https://archive.org/metadata/" + show_data[:dir] + "/"
 
         puts "🌹💀 Downloading #{name}"
     end
     
     # Converts track lists to Track objects
-    def set_tracks(track_data)
-        @tracks = track_data.map { |track| Track.new(track) }
+    def set_tracks(files)
+        audio_files = files.select { |file| audio_file?(file) }
+                            .select { |file| matches_format?(file, @format) }
+                            
+        if audio_files.empty?
+            puts "❌ No #{@format} files found"
+            return []
+        end
+  
+        @tracks = audio_files.map { |track| Track.new(track) }
+    end
+
+    private
+
+    def audio_file?(file)
+        %w[mp3 flac ogg m4a].include?(File.extname(file["name"]).delete('.'))
+    end
+
+    def matches_format?(file, format)
+        File.extname(file["name"]).delete('.') == format
     end
 end

data/lib/deadlist/models/track.rb

@@ -1,24 +1,9 @@
 class Track
-  attr_reader :pos, :name, :links
+  attr_reader :pos, :title, :filename
 
   def initialize(track_data)
-    @pos = track_data[:pos]
-    @name = track_data[:name]
-    @links = track_data[:links]
-  end
-
-  # Returns formats available for a given track via the links
-  def available_formats
-    @available_formats ||= links.map { |url| File.extname(url).delete('.') }
-  end
-
-  # Based on the format argument, returns one link containing that format
-  def url_for_format(format)
-    links.find { |url| url.end_with?(".#{format}") }
-  end
-
-  # Returns boolean if a format exists for this Track
-  def has_format?(format)
-    available_formats.include?(format)
+    @pos = track_data["track"]
+    @title = track_data["title"]
+    @filename = track_data["name"]
   end
 end

data/lib/deadlist.rb

@@ -7,20 +7,25 @@ require_relative 'deadlist/cli.rb'
 
 # Main DeadList class.
 class DeadList
-    HOSTNAME = 'https://www.archive.org/'
-
     def initialize
-        @current_version = '1.0.1'
-        @hostname = HOSTNAME
+        @current_version = '1.1.0'
     end
 
+    # Argument abstraction should probably happen at this level!
+
     def run        
         # Start a new CLI session
         # In future this could be abstracted to pass the show link vs all args, so a 'session' is started per show.
         session = CLI.new(@current_version, ARGV)
 
         # Scrape links and metadata for given show
-        session.scrape_links
+        session.create_show
+
+        # In future, consider starting multiple downloaders for a list of shows
+        # show_list = session.args[:shows]
+        # show_list.each do |show|
+        #   session.download_show(show)
+        # end
 
         # Create folder with show date and begin track downloads if format matches
         session.download_show

metadata

@@ -1,13 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: deadlist
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.1.0
 platform: ruby
 authors:
 - nazwr
+autorequire:
 bindir: bin
 cert_chain: []
-date: 1980-01-02 00:00:00.000000000 Z
+date: 2025-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
@@ -48,15 +49,16 @@ files:
 - bin/deadlist
 - lib/deadlist.rb
 - lib/deadlist/cli.rb
+- lib/deadlist/cli/argument_parser.rb
 - lib/deadlist/cli/client.rb
 - lib/deadlist/cli/downloader.rb
 - lib/deadlist/models/show.rb
 - lib/deadlist/models/track.rb
-- lib/version.rb
 homepage: https://github.com/nazwr/deadlist
 licenses:
 - MIT
 metadata: {}
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -71,7 +73,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.7
+rubygems_version: 3.4.19
+signing_key:
 specification_version: 4
 summary: Download Grateful Dead shows from archive.org
 test_files: []

data/lib/version.rb

@@ -1,3 +0,0 @@
-module DeadList
-  VERSION = '1.0.0'
-end