imgfetcha 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 85a525ae878b7bdb3a04929960bae1c2a346efaca5774a1a78b51cdbf003259e
+  data.tar.gz: cc85354908698f73e8b7d96a9c4343f1394df2cf2fd97c69edf7242fe0549c91
+SHA512:
+  metadata.gz: 55c26e1b660266ff2949c4a220e855ef5530edb6f3261d1fd5c19075d36387184d30d636b8323d1f867726de68535a16df8a0a45db195f7ccd35ab51898a1a2a
+  data.tar.gz: 61577dcbe5f68f9ad96c9c4c2aebfcf61fc7a031774e854cb27e21169dd9f640512e48813e354abf6ee9d94a90ad4e6be2b47eb983ee23f4cead0c21ee212a95

data/bin/imgfetcha

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+require 'imgfetcha'
+
+begin
+  Imgfetcha.run
+end

data/lib/imgfetcha.rb

@@ -0,0 +1,22 @@
+require 'imgfetcha/version'
+require 'imgfetcha/arg_parser'
+require 'imgfetcha/file_reader'
+require 'imgfetcha/batch_fetcher'
+require 'imgfetcha/errors/input_file_not_specified_error'
+require 'imgfetcha/errors/no_urls_found_error'
+
+module Imgfetcha
+  def self.run
+    parser = ArgParser.new
+    options = parser.run
+
+    reader = FileReader.new(options)
+    reader.run
+
+    downloader = BatchFetcher.new(reader.result, options)
+    downloader.run
+  rescue StandardError, NotImplementedError => e
+    puts e.class, e.message
+    puts e.backtrace if options[:verbose]
+  end
+end

data/lib/imgfetcha/arg_parser.rb

@@ -0,0 +1,48 @@
+require 'optparse'
+
+module Imgfetcha
+  class ArgParser
+    attr_accessor :result
+
+    def initialize
+      @result = {}
+    end
+
+    def run
+      execute_parser
+      @result
+    end
+
+    private
+
+    # rubocop:disable Metrics/MethodLength
+    def execute_parser
+      OptionParser.new do |opts|
+        opts.banner = 'Usage: imgfetcha -i INPUT_FILE -o OUTPUT_DIRECTORY'
+
+        opts.on('-v', '--[no-]verbose', 'Run verbosely') do |v|
+          @result[:verbose] = v
+        end
+
+        opts.on('-i INPUT_FILE', '--input=INPUT_FILE', 'Specify input file') do |i|
+          @result[:input_file] = i
+        end
+
+        opts.on('-o OUTPUT_DIRECTORY', '--output=OUTPUT_DIRECTORY', 'Specify output directory') do |o|
+          @result[:output_dir] = o
+        end
+
+        opts.on('-V', '--version', 'Print version') do
+          puts Imgfetcha::VERSION
+          exit
+        end
+
+        opts.on('-h', '--help', 'Print this help') do
+          puts opts
+          exit
+        end
+      end.parse!
+    end
+    # rubocop:enable Metrics/MethodLength
+  end
+end

data/lib/imgfetcha/batch_fetcher.rb

@@ -0,0 +1,69 @@
+require 'open-uri'
+require 'mime/types'
+
+module Imgfetcha
+  class BatchFetcher
+    # NOTE: 'bin' stands for `application/octet-stream`
+    VALID_TYPES = %w[jpeg jpg png gif heic bin].freeze
+
+    attr_reader :urls, :output_dir, :result
+
+    def initialize(urls, options)
+      @urls       = urls
+      @output_dir = options[:output_dir] || Dir.pwd
+      @verbose    = options[:verbose]
+    end
+
+    def run
+      @result = batch_download
+      puts "\nDownloaded #{@result.count} images"
+      @result
+    end
+
+    private
+
+    def batch_download
+      urls.map.with_index do |url, i|
+        print_progress(url, i)
+        temp_file = URI.open(url)
+        type      = detect_type(temp_file)
+
+        next unless validate_type(type)
+
+        write_file(temp_file: temp_file, name: file_name(url, temp_file))
+        url
+      end.compact
+    end
+
+    # Get basename from a URL
+    def file_name(url, file)
+      name = File.basename(URI.parse(url).path)
+      # Append type if valid types aren't contained in the name
+      name += ".#{detect_type(file)}" unless VALID_TYPES.any? { |type| name.include?(type) }
+
+      name
+    end
+
+    def write_file(temp_file:, name:)
+      File.open("#{@output_dir}/#{name}", 'wb') do |f|
+        f.write(temp_file.read) ? print('OK') : print('ERROR')
+      end
+    end
+
+    def detect_type(file)
+      content_type = file.meta['content-type']
+      MIME::Types[content_type].first.preferred_extension
+    end
+
+    def validate_type(type)
+      return true if VALID_TYPES.include?(type)
+
+      print("ERROR: Type #{type} is invalid")
+      false
+    end
+
+    def print_progress(url, index)
+      print "\n[#{index + 1}/#{@urls.count}] Downloading #{url} "
+    end
+  end
+end

data/lib/imgfetcha/errors/input_file_not_specified_error.rb

@@ -0,0 +1,11 @@
+module Imgfetcha
+  class FileReader
+    class InputFileNotSpecifiedError < StandardError
+      attr_reader :message
+
+      def initialize
+        @message = "Input file was not specified. Please provide the input file with '-i INPUT_FILE'"
+      end
+    end
+  end
+end

data/lib/imgfetcha/errors/no_urls_found_error.rb

@@ -0,0 +1,11 @@
+module Imgfetcha
+  class FileReader
+    class NoUrlsFoundError < StandardError
+      attr_reader :message
+
+      def initialize
+        @message = "The input file doesn't seem to have any valid URLs"
+      end
+    end
+  end
+end

data/lib/imgfetcha/file_reader.rb

@@ -0,0 +1,40 @@
+module Imgfetcha
+  class FileReader
+    attr_reader :input_file, :result
+
+    def initialize(options)
+      @input_file = options[:input_file]
+      @verbose    = options[:verbose]
+    end
+
+    def run
+      read_file
+      filter_urls
+      report_results if @verbose
+      @result
+    end
+
+    private
+
+    def read_file
+      raise InputFileNotSpecifiedError unless @input_file
+
+      # Expand path so that Dir#chdir would understand paths relative to home
+      @contents = File.read(File.expand_path(@input_file)).split
+    end
+
+    def filter_urls
+      @result = @contents.select { |url| URI.parse(url).is_a?(URI::HTTP) }
+      raise NoUrlsFoundError if @result.empty?
+
+      # TODO: group valid and unvalid URLs, warn about invalid ones
+
+      @result
+    end
+
+    def report_results
+      puts "Found #{@result.count} URLs in #{@contents.count} lines:"
+      puts @result
+    end
+  end
+end

data/lib/imgfetcha/version.rb

@@ -0,0 +1,3 @@
+module Imgfetcha
+  VERSION = '0.2.0'.freeze
+end

metadata

@@ -0,0 +1,112 @@
+--- !ruby/object:Gem::Specification
+name: imgfetcha
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- ston1x
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-07-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mime-types
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.13.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.13.1
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.9.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.9.0
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.88.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.88.0
+description: Uses input file as a list of URLs and downloads all the images
+email:
+- stoianovnk@gmail.com
+executables:
+- imgfetcha
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/imgfetcha
+- lib/imgfetcha.rb
+- lib/imgfetcha/arg_parser.rb
+- lib/imgfetcha/batch_fetcher.rb
+- lib/imgfetcha/errors/input_file_not_specified_error.rb
+- lib/imgfetcha/errors/no_urls_found_error.rb
+- lib/imgfetcha/file_reader.rb
+- lib/imgfetcha/version.rb
+homepage: https://github.com/ston1x/imgfetcha
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/ston1x/imgfetcha
+  source_code_uri: https://github.com/ston1x/imgfetcha
+  changelog_uri: https://github.com/ston1x/imgfetcha
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key: 
+specification_version: 4
+summary: Ruby gem that takes an input of image URLs and downloads them in batch
+test_files: []