tenet 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: d95fc0a698fc1275f6c1d3980fc06db6e67080e89cbf6fef3964c16bba7e99c4
+  data.tar.gz: 61a30e95a4804e3248b312b67b7d6b6071e91b27d512ba3b827c679c05719868
+SHA512:
+  metadata.gz: 45a24af30c860b04ea37b71e7bc2495f37d501b7c3113a54754564d637bf0cdb616951439e23b6967793040927324abaab0d25c8e2a8c0404cbca476c6e1b7bd
+  data.tar.gz: ce5123dd2816bbef874509d33fa816f72c23292e44ab540d0c9a170e12457d26a07cd1231bc06e32b86d7a3cdfd6f06d797a3acf136e27a29b07030a649ec52d

data/.rspec

@@ -0,0 +1,4 @@
+--format documentation
+--color
+--require spec_helper
+--require rspec-power_assert

data/.ruby-version

@@ -0,0 +1 @@
+3.0.3

data/Gemfile

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+group :development do
+  gem "rake", "~> 13.0"
+  gem "rspec", "~> 3.0"
+  gem "rspec-power_assert"
+  gem "webrick"
+  gem "yard"
+end

data/Gemfile.lock

@@ -0,0 +1,38 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.5.0)
+    power_assert (1.1.7)
+    rake (13.0.6)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-mocks (3.10.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-power_assert (1.1.0)
+      power_assert (~> 1.1.0)
+      rspec (>= 2.14)
+    rspec-support (3.10.3)
+    webrick (1.7.0)
+    yard (0.9.27)
+      webrick (~> 1.7.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  rake (~> 13.0)
+  rspec (~> 3.0)
+  rspec-power_assert
+  webrick
+  yard
+
+BUNDLED WITH
+   2.2.32

data/README.md

@@ -0,0 +1,69 @@
+# Tenet
+
+Tenet restores HTML elements views to Array of Hash data.
+It provides a API for mapping to HTML scraping rules and data attributes.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'tenet'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install tenet
+
+## Usage
+
+Import from a index page:
+
+```ruby
+require "tenet"
+
+class Events < Tenet::IndexPage
+  url "https://example.com/events"
+
+  row ".event"
+
+  attribute :name, css: ".event__title", type: :string
+  attribute :link, css: ".event__link", type: :link
+  attribute :thumbnail, css: ".event__thumbnail", type: :img
+  attribute :status, css: ".event__status", type: :string
+end
+
+Events.new.to_a
+```
+
+Import from multiple show pages:
+
+```ruby
+
+require "tenet"
+
+class Events < Tenet::MultiPage
+  urls [
+    "https://example.com/events/1",
+    "https://example.com/events/2",
+    "https://example.com/events/3"
+  ]
+
+  attribute :name, css: ".event__title", type: :string
+  attribute :link, css: ".event__link", type: :link
+  attribute :thumbnail, css: ".event__thumbnail", type: :img
+  attribute :status, css: ".event__status", type: :string
+end
+
+Events.new.to_a
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).

data/Rakefile

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require "yard"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec
+
+YARD::Rake::YardocTask.new do |t|
+  t.files = ['lib/**/*.rb']
+end

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "bundler/setup"
+require "tenet"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/tenet/attribute.rb

@@ -0,0 +1,19 @@
+module Tenet
+  class Attribute
+    TYPE_OPTIONS = [:string, :img, :link]
+
+    attr_accessor :name, :css, :type
+
+    #
+    # @param [Symbol] name
+    # @param [String] css
+    # @param [Symbol] type
+    #
+    def initialize(name, css:, type: :string)
+      raise ArgumentError unless TYPE_OPTIONS.include?(type)
+      @name = name
+      @css = css
+      @type = type
+    end
+  end
+end

data/lib/tenet/index_page.rb

@@ -0,0 +1,48 @@
+module Tenet
+  class IndexPage
+
+    @@url = ""
+    @@row = ""
+    @@attributes = []
+
+    class << self
+      #
+      # @param [String] url
+      #
+      def url(url)
+        @@url = url
+      end
+
+      #
+      # @param [String] css
+      #
+      def row(css)
+        @@row = css
+      end
+
+      #
+      # @param [Symbol] name
+      # @param [String] css
+      # @param [Symbol] type
+      #
+      def attribute(name, css:, type: :string)
+        @@attributes << Attribute.new(name, css: css, type: type)
+      end
+    end
+
+    def initialize
+      @collection = []
+
+      Page.new(@@url).document.css(@@row).each do |row_document|
+        @collection << Row.new(row_document.to_html, @@attributes).to_h
+      end
+    end
+
+    #
+    # @return [Array<Hash>]
+    #
+    def to_a
+      @collection
+    end
+  end
+end

data/lib/tenet/multi_pages.rb

@@ -0,0 +1,41 @@
+module Tenet
+  class MultiPages
+
+    @@urls = []
+    @@attributes = []
+
+    class << self
+      #
+      # @param [Array] urls
+      #
+      def urls(urls)
+        @@urls = urls
+      end
+
+      #
+      # @param [Symbol] name
+      # @param [String] css
+      # @param [Symbol] type
+      #
+      def attribute(name, css:, type: :string)
+        @@attributes << Attribute.new(name, css: css, type: type)
+      end
+    end
+
+    def initialize
+      @collection = []
+
+      @@urls.each do |url|
+        html = Page.new(url).html
+        @collection << Row.new(html, @@attributes).to_h
+      end
+    end
+
+    #
+    # @return [Array<Hash>]
+    #
+    def to_a
+      @collection
+    end
+  end
+end

data/lib/tenet/page.rb

@@ -0,0 +1,17 @@
+require "nokogiri"
+require "open-uri"
+
+module Tenet
+  class Page
+
+    attr_accessor :html, :document
+
+    #
+    # @param [String] url
+    #
+    def initialize(url, parser = Nokogiri::HTML5)
+      @html = URI.open(url).string
+      @document = parser.parse(@html)
+    end
+  end
+end

data/lib/tenet/row.rb

@@ -0,0 +1,39 @@
+require "nokogiri"
+
+module Tenet
+  class Row
+    #
+    # @param [String] html
+    # @param [Hash] attributes
+    #
+    def initialize(html, attributes, parser = Nokogiri::HTML5)
+      @html = html
+      @attributes = attributes
+      @document = parser.parse(@html)
+    end
+
+    #
+    # @return [Hash]
+    #
+    def to_h
+      values = {}
+
+      @attributes.each do |attribute|
+        selector = @document.css(attribute.css).first
+
+        case attribute.type
+        when :string
+          value = selector.content
+        when :link
+          value = selector[:href]
+        when :img
+          value = selector[:src]
+        end
+
+        values[attribute.name] = value
+      end
+
+      values
+    end
+  end
+end

data/lib/tenet/version.rb

@@ -0,0 +1,3 @@
+module Tenet
+  VERSION = "1.0.0"
+end

data/lib/tenet.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+Dir.glob(__dir__ + "/tenet/**/*.rb").each { |f| require_relative f }
+
+module Tenet
+end

data/tenet.gemspec

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+require_relative "lib/tenet/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "tenet"
+  spec.version = Tenet::VERSION
+  spec.authors = ["moekidev"]
+  spec.email = ["me@moeki.dev"]
+  spec.license = "MIT"
+
+  spec.summary = "Tenet restores HTML elements views to Array of Hash data."
+  spec.description = <<~EOF
+    Tenet restores HTML elements views to Array of Hash data.
+    It provides a API for mapping to HTML scraping rules and
+    data attributes.
+  EOF
+  spec.homepage = "https://github.com/moekidev/tenet"
+  spec.required_ruby_version = ">= 2.6.0"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/moekidev/tenet"
+
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (f == __FILE__) || f.match(%r{\A(?:(?:test|spec|features)/|\.(?:git|travis|circleci)|appveyor)})
+    end
+  end
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "nokogiri", "~> 1.0"
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification
+name: tenet
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- moekidev
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2021-12-31 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+description: |
+  Tenet restores HTML elements views to Array of Hash data.
+  It provides a API for mapping to HTML scraping rules and
+  data attributes.
+email:
+- me@moeki.dev
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".DS_Store"
+- ".rspec"
+- ".ruby-version"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/tenet.rb
+- lib/tenet/attribute.rb
+- lib/tenet/index_page.rb
+- lib/tenet/multi_pages.rb
+- lib/tenet/page.rb
+- lib/tenet/row.rb
+- lib/tenet/version.rb
+- tenet.gemspec
+homepage: https://github.com/moekidev/tenet
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/moekidev/tenet
+  source_code_uri: https://github.com/moekidev/tenet
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.32
+signing_key: 
+specification_version: 4
+summary: Tenet restores HTML elements views to Array of Hash data.
+test_files: []