favicon_gem 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 968a02874daebda7085218d3f92dc00e4363e173c55f19548f4c92ce5d726264
+  data.tar.gz: 78f7ecfd4326b6104a1f69b8df06ba7faaf0e6901b06be0e0f455e4343080f29
+SHA512:
+  metadata.gz: d9ed6ec4017bcf457324229777636410dfbc12ee8ece545e306c5f5eda61e770878e0b137ad6d2385a25a0a9e3587d3417e92ae2ab1e6fe513572509364a677c
+  data.tar.gz: de2d8bfe54132424873ff4718c1a283ac4f918ae545376c256ba6b82f520101095719e5cd14d05503d223741d576ff6f026ea6e0ff59395540fa3b4887290005

data/README.md

@@ -0,0 +1,83 @@
+# FaviconGem
+
+FaviconGem is a Ruby gem for finding and retrieving website favicons (icons). It's a port of the popular [favicon](https://github.com/scottwernervt/favicon) Python library.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'favicon_gem'
+```
+
+And then execute:
+
+```bash
+$ bundle install
+```
+
+Or install it manually:
+
+```bash
+$ gem install favicon_gem
+```
+
+## Usage
+
+### Get all icons
+
+```ruby
+require 'favicon_gem'
+
+icons = FaviconGem.get('https://www.ruby-lang.org/')
+# => [Icon, Icon, Icon, ...]
+
+# The first icon is usually the largest
+icon = icons.first
+puts "URL: #{icon.url}"
+puts "Size: #{icon.width}x#{icon.height}"
+puts "Format: #{icon.format}"
+```
+
+### Download an icon
+
+```ruby
+require 'favicon_gem'
+require 'open-uri'
+
+icons = FaviconGem.get('https://www.ruby-lang.org/')
+icon = icons.first
+
+URI.open(icon.url) do |image|
+  File.open("/tmp/ruby-favicon.#{icon.format}", "wb") do |file|
+    file.write(image.read)
+  end
+end
+
+# => /tmp/ruby-favicon.png
+```
+
+### Additional parameters
+
+```ruby
+require 'favicon_gem'
+
+# Custom headers
+headers = {
+  'User-Agent' => 'My custom User-Agent'
+}
+
+# Timeout and other parameters
+FaviconGem.get('https://www.ruby-lang.org/',
+                headers: headers,
+                timeout: 5)
+```
+
+## Requirements
+
+* [nokogiri](https://github.com/sparklemotion/nokogiri) - for HTML parsing
+* [faraday](https://github.com/lostisland/faraday) - for HTTP requests
+
+## License
+
+This gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/lib/favicon_gem/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module FaviconGem
+  VERSION = "0.1.0"
+end

data/lib/favicon_gem.rb

@@ -0,0 +1,207 @@
+# frozen_string_literal: true
+
+require "favicon_gem/version"
+require "faraday"
+require "faraday/follow_redirects"
+require "nokogiri"
+require "uri"
+require "set"
+
+module FaviconGem
+  class Error < StandardError; end
+
+  # Website icon representation
+  Icon = Struct.new(:url, :width, :height, :format)
+
+  # Gem metadata
+  TITLE = "favicon_gem"
+  AUTHOR = "Ported from Python favicon by Scott Werner"
+  LICENSE = "MIT"
+
+  HEADERS = {
+    "User-Agent" => "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) " \
+                   "AppleWebKit/537.36 (KHTML, like Gecko) " \
+                   "Chrome/33.0.1750.152 Safari/537.36"
+  }
+
+  LINK_RELS = [
+    "icon",
+    "shortcut icon",
+    "apple-touch-icon",
+    "apple-touch-icon-precomposed"
+  ]
+
+  META_NAMES = ["msapplication-TileImage"]  # Removed og:image from metatags as it's usually not a favicon
+
+  # Format priorities (higher = better)
+  FORMAT_PRIORITY = {
+    "ico" => 10,
+    "png" => 9,
+    "jpg" => 8,
+    "jpeg" => 7,
+    "svg" => 6,
+    "gif" => 5,
+    "" => 0  # Unknown format has the lowest priority
+  }
+
+  SIZE_RE = /(?<width>\d{2,4})x(?<height>\d{2,4})/i
+
+  class << self
+    # Get all icons for a URL
+    #
+    # @param url [String] Page URL
+    # @param headers [Hash] Request headers
+    # @return [Array<Icon>] List of found icons, sorted by size
+    def get(url, headers: HEADERS, **request_options)
+      request_options[:headers] ||= headers
+
+      conn = Faraday.new(url: url) do |faraday|
+        faraday.request :url_encoded
+        faraday.headers = request_options[:headers]
+        faraday.options.timeout = request_options[:timeout] if request_options[:timeout]
+        faraday.use Faraday::FollowRedirects::Middleware
+        faraday.adapter Faraday.default_adapter
+      end
+
+      response = conn.get
+      raise Error, "Failed to fetch URL: #{response.status}" unless response.success?
+
+      icons = Set.new
+
+      default_icon = default(response.env.url.to_s, **request_options)
+      icons.add(default_icon) if default_icon
+
+      link_icons = tags(response.env.url.to_s, response.body)
+      icons.merge(link_icons) if link_icons.any?
+
+      # Improve sorting:
+      # 1. By size (larger first)
+      # 2. If sizes are equal, sort by format (ico/png have higher priority)
+      # 3. All icons with zero sizes go to the end
+      icons.to_a.sort_by do |icon|
+        format_priority = FORMAT_PRIORITY[icon.format] || 0
+        size = icon.width + icon.height
+
+        if size > 0
+          [1, size, format_priority]  # Icons with non-zero size first
+        else
+          [0, format_priority]        # Zero sizes - second priority
+        end
+      end.reverse
+    end
+
+    private
+
+    # Get icon using default filename favicon.ico
+    #
+    # @param url [String] Site URL
+    # @param request_options [Hash] Request parameters
+    # @return [Icon, nil] Icon or nil
+    def default(url, **request_options)
+      uri = URI.parse(url)
+      favicon_url = "#{uri.scheme}://#{uri.host}/favicon.ico"
+
+      conn = Faraday.new(url: favicon_url) do |faraday|
+        faraday.headers = request_options[:headers] if request_options[:headers]
+        faraday.options.timeout = request_options[:timeout] if request_options[:timeout]
+        faraday.use Faraday::FollowRedirects::Middleware
+        faraday.adapter Faraday.default_adapter
+      end
+
+      response = conn.head
+      return Icon.new(response.env.url.to_s, 0, 0, "ico") if response.success?
+      nil
+    rescue Faraday::Error
+      nil
+    end
+
+    # Get icons from link and meta tags
+    #
+    # @param url [String] Site URL
+    # @param html [String] Page HTML code
+    # @return [Set<Icon>] Found icons
+    def tags(url, html)
+      doc = Nokogiri::HTML(html)
+      icons = Set.new
+
+      # Search in <link> tags
+      link_tags = Set.new
+      LINK_RELS.each do |rel|
+        doc.css("link[rel='#{rel}'][href]").each do |link_tag|
+          link_tags.add(link_tag)
+        end
+      end
+
+      # Search in <meta> tags
+      meta_tags = Set.new
+      META_NAMES.each do |name|
+        doc.css("meta[name='#{name}'][content], meta[property='#{name}'][content]").each do |meta_tag|
+          meta_tags.add(meta_tag)
+        end
+      end
+
+      (link_tags | meta_tags).each do |tag|
+        href = tag["href"] || tag["content"] || ""
+        href = href.strip
+
+        next if href.empty? || href.start_with?("data:image/")
+
+        url_parsed = if is_absolute(href)
+                      href
+                    else
+                      URI.join(url, href).to_s
+                    end
+
+        # Fix URLs like '//cdn.network.com/favicon.png'
+        uri = URI.parse(url)
+        parsed_uri = URI.parse(url_parsed)
+        if parsed_uri.scheme.nil? && parsed_uri.host.nil? && parsed_uri.path.start_with?("//")
+          url_parsed = "#{uri.scheme}:#{parsed_uri.path}"
+        end
+
+        width, height = dimensions(tag)
+        ext = File.extname(URI.parse(url_parsed).path)[1..]&.downcase || ""
+
+        icons.add(Icon.new(url_parsed, width, height, ext))
+      end
+
+      icons
+    end
+
+    # Check if URL is absolute
+    #
+    # @param url [String] URL
+    # @return [Boolean] true if absolute
+    def is_absolute(url)
+      uri = URI.parse(url)
+      !uri.host.nil?
+    rescue URI::InvalidURIError
+      false
+    end
+
+    # Get icon dimensions from size attribute or filename
+    #
+    # @param tag [Nokogiri::XML::Element] Link or meta tag
+    # @return [Array<Integer>] Width and height, or [0,0]
+    def dimensions(tag)
+      sizes = tag["sizes"]
+      if sizes && sizes != "any"
+        size = sizes.split(" ").max_by { |s| s.scan(/\d+/).map(&:to_i).sum }
+        width, height = size.split(/[x×]/)
+      else
+        filename = tag["href"] || tag["content"] || ""
+        size = SIZE_RE.match(filename)
+        if size
+          width, height = size[:width], size[:height]
+        else
+          width, height = "0", "0"
+        end
+      end
+
+      # Clean non-digit characters
+      width = width.to_s.scan(/\d+/).join
+      height = height.to_s.scan(/\d+/).join
+      [width.to_i, height.to_i]
+    end
+  end
+end

metadata

@@ -0,0 +1,148 @@
+--- !ruby/object:Gem::Specification
+name: favicon_gem
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ivan Nemytchenko
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2025-04-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+- !ruby/object:Gem::Dependency
+  name: faraday
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+- !ruby/object:Gem::Dependency
+  name: faraday-follow_redirects
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.18'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.18'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.50'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.50'
+description: favicon_gem is a Ruby library to find a website's favicon, ported from
+  Python's favicon library
+email:
+- nemytchenko@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/favicon_gem.rb
+- lib/favicon_gem/version.rb
+homepage: https://github.com/inem/favicon
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/inem/favicon
+  source_code_uri: https://github.com/inem/favicon
+  changelog_uri: https://github.com/inem/favicon/blob/main/CHANGELOG.md
+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: Ruby gem to find a website's favicon
+test_files: []