forki 0.1.1

data/lib/forki/user.rb

@@ -0,0 +1,45 @@
+# frozen_string_literal: true
+
+module Forki
+  class User
+    def self.lookup(urls = [])
+      urls = [urls] unless urls.kind_of?(Array)
+      self.scrape(urls)
+    end
+
+    attr_reader :name,
+                :id,
+                :number_of_followers,
+                :verified,
+                :profile,
+                :profile_link,
+                :profile_image_file,
+                :profile_image_url,
+                :number_of_likes
+
+    private
+
+      def initialize(user_hash = {})
+        @name = user_hash[:name]
+        @id = user_hash[:id]
+        @number_of_followers = user_hash[:number_of_followers]
+        @verified = user_hash[:verified]
+        @profile = user_hash[:profile]
+        @profile_link = user_hash[:profile_link]
+        @profile_image_file = user_hash[:profile_image_file]
+        @profile_image_url = user_hash[:profile_image_url]
+        @number_of_likes = user_hash[:number_of_likes]
+      end
+
+      class << self
+        private
+
+          def scrape(urls)
+            urls.map do |url|
+              user_hash = Forki::UserScraper.new.parse(url)
+              User.new(user_hash)
+            end
+          end
+      end
+  end
+end

data/lib/forki/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Forki
+  VERSION = "0.1.1"
+end

data/lib/forki.rb

@@ -0,0 +1,98 @@
+# frozen_string_literal: true
+
+require_relative "forki/version"
+
+# Representative objects we create
+require_relative "forki/user"
+require_relative "forki/post"
+
+require "helpers/configuration"
+require_relative "forki/scrapers/scraper"
+
+module Forki
+  extend Configuration
+
+  @@forki_logger = Logger.new(STDOUT)
+
+  class Error < StandardError; end
+  class RetryableError < Error; end
+
+  class InvalidUrlError < StandardError
+    def initialize(msg = "Url must be a proper Facebook Url")
+      super
+    end
+  end
+
+  class ContentUnavailableError < StandardError
+    def initialize(msg = "Post no longer available")
+      super
+    end
+  end
+
+  class MissingCredentialsError < StandardError
+    def initalize(msg = "Missing FACEBOOK_EMAIL or FACEBOOK_PASSWORD environment variable")
+      super
+    end
+  end
+
+  class BlockedCredentialsError < StandardError
+    def initalize(msg = "Credentials are most likely being blocked")
+      super
+    end
+  end
+
+  class UnhandledContentError < StandardError
+    def initialize(msg = "Forki does not know how to handle the post")
+      super
+    end
+  end
+
+  define_setting :temp_storage_location, "tmp/forki"
+
+  # Extract the file extension from a media URL
+  # E.g. ".png" from https://scontent-atl3-2.xx.fbcdn.net/v/t39.30808-1.png?stp=dst-png_p148x148
+  def self.extract_file_extension_from_url(url)
+    stripped_url = url.split("?").first  # remove URL query params
+    extension = stripped_url.split(".").last
+
+    extension = nil unless /^[a-zA-Z0-9]{3}$/.match?(extension)  # extension must be a 3-character alphanumeric string
+    extension = ".#{extension}" unless extension.nil?
+    extension
+  end
+
+  # Get an image from a URL and save to a temp folder set in the configuration under
+  # temp_storage_location
+  def self.retrieve_media(url)
+    @@forki_logger.debug("Forki download started: #{url}")
+    start_time = Time.now
+
+    response = Typhoeus.get(url)
+
+    extension = Forki.extract_file_extension_from_url(url)
+    temp_file = "#{Forki.temp_storage_location}/facebook_media_#{SecureRandom.uuid}#{extension}"
+
+    # We do this in case the folder isn't created yet, since it's a temp folder we'll just do so
+    create_temp_storage_location
+    File.binwrite(temp_file, response.body)
+
+    @@forki_logger.debug("Forki download finished")
+    @@forki_logger.debug("Save Location: #{temp_file}")
+    @@forki_logger.debug("Size: #{(File.size("./#{temp_file}").to_f / 1024 / 1024).round(4)} MB")
+    @@forki_logger.debug("Time to Download: #{(Time.now - start_time).round(3)} seconds")
+    temp_file
+  end
+
+  def self.create_temp_storage_location
+    return if File.exist?(Forki.temp_storage_location) && File.directory?(Forki.temp_storage_location)
+
+    FileUtils.mkdir_p Forki.temp_storage_location
+  end
+
+  def self.set_logger_level
+    if ENV["RAILS_ENV"] == "test" || ENV["RAILS_ENV"] == "development"
+      @@forki_logger.level = Logger::INFO
+    else
+      @@forki_logger.level = Logger::WARN
+    end
+  end
+end

data/lib/generators/forki.rb

@@ -0,0 +1,3 @@
+forki.configuration do |config|
+  config.temp_storage_location = "tmp/forki"
+end

data/lib/generators/forki_generator.rb

@@ -0,0 +1,6 @@
+class ForkiGenerator < Rails::Generators::Base
+  source_root(File.expand_path(File.dirname(__FILE__)))
+  def copy_initializer
+    copy_file "forki.rb", "config/initializers/forki.rb"
+  end
+end

data/lib/helpers/configuration.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+# Borrowed with thanks from https://www.viget.com/articles/easy-gem-configuration-variables-with-defaults/
+module Configuration
+  def configuration
+    yield self
+  end
+
+  def define_setting(name, default = nil)
+    class_variable_set("@@#{name}", default)
+
+    define_class_method "#{name}=" do |value|
+      class_variable_set("@@#{name}", value)
+    end
+
+    define_class_method name do
+      class_variable_get("@@#{name}")
+    end
+  end
+
+ private
+
+   def define_class_method(name, &block)
+     (class << self; self; end).instance_eval do
+       define_method name, &block
+     end
+   end
+end

metadata

@@ -0,0 +1,146 @@
+--- !ruby/object:Gem::Specification
+name: forki
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- ''
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2023-05-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: capybara
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: apparition
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: typhoeus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: oj
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: selenium-webdriver
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description:
+email:
+- ''
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/main.yml"
+- ".gitignore"
+- ".rubocop.yml"
+- ".ruby-version"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- forki.gemspec
+- lib/forki.rb
+- lib/forki/post.rb
+- lib/forki/scrapers/post_scraper.rb
+- lib/forki/scrapers/scraper.rb
+- lib/forki/scrapers/user_scraper.rb
+- lib/forki/user.rb
+- lib/forki/version.rb
+- lib/generators/forki.rb
+- lib/generators/forki_generator.rb
+- lib/helpers/configuration.rb
+- reactions/.DS_Store
+- reactions/angry.png
+- reactions/care.png
+- reactions/haha.png
+- reactions/like.png
+- reactions/love.png
+- reactions/pride.png
+- reactions/sad.png
+- reactions/wow.png
+homepage:
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.26
+signing_key:
+specification_version: 4
+summary: A gem to scrape Facebook pages for archive purposes.
+test_files: []