google_font_extractor 0.0.1

data/README.md

@@ -0,0 +1,22 @@
+# Introduction
+
+The GoogleFontExtractor Gem will crawl the Google Webfonts directory on your command and return an array of Struct instances with details of fonts available in the Google Fonts directory.
+
+PLEASE Note: this does NOT download the font files themselves.
+
+Let's get started.
+
+## 1. In your Gemfile
+    gem "google_font_extractor"
+
+## 2. Bundle Install
+
+## 3. rails console example
+    ruby-1.9.2> fonts = GoogleFontExtractor.extract
+    ruby-1.9.2> fonts.first
+    => #<struct designer="Steve Matteson", name="Droid Serif", charsets=["latin"], weights_count="4", weights=["regular", "italic", "bold", "bolditalic"], families_count=nil, category="serif"> 
+    ruby-1.9.2>
+
+
+# Additional notes
+If you want to do anything real with this, you should save the results of the extract method to a YAML file or database table.

data/google_font_extractor.gemspec

@@ -0,0 +1,40 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib/', __FILE__)
+$:.unshift lib unless $:.include?(lib)
+ 
+require 'version'
+ 
+Gem::Specification.new do |s|
+  s.name        = "google_font_extractor"
+  s.version     = GoogleFontExtractor::VERSION
+  s.platform    = Gem::Platform::RUBY
+  s.authors     = ["Jason Lambert"]
+  s.email       = ["mail@jasonlambert.co.uk"]
+  s.homepage    = "https://github.com/mendable/google-font-extractor"
+  s.summary     = "Extracts a list of all fonts available via the Google Webfonts API"
+  s.description = "Extracts a list of all fonts available via the Google Webfonts API, including details of character sets supported, weights, and categorization."
+
+  s.required_rubygems_version = ">= 1.3.6"
+ 
+  s.files        = Dir.glob("lib/*") + %w(README.md google_font_extractor.gemspec)
+  s.require_paths = ['lib']
+  s.rubyforge_project = %q{[none]}
+
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<tidy_ffi>, [">= 0.1.3"])
+      s.add_runtime_dependency(%q<scrapi>, [">= 2.0.0"])
+    else
+      s.add_dependency(%q<tidy_ffi>, [">= 0.1.3"])
+      s.add_dependency(%q<scrapi>, [">= 2.0.0"])
+    end
+  else
+    s.add_dependency(%q<tidy_ffi>, [">= 0.1.3"])
+    s.add_dependency(%q<scrapi>, [">= 2.0.0"])
+  end
+
+end

data/lib/extract.rb

@@ -0,0 +1,68 @@
+module GoogleFontExtractor
+  module Extract
+
+    # Individual Font details page
+    class FontPage < Scraper::Base
+      array :weights
+
+      process("#_variants span.parametername", :weights => :text) do |el|
+        @weights.each_with_index do |r, idx|
+          if r =~ /Web Fonts API parameter name: (.*)/ then
+            @weights[idx] = $1.split(':').size == 1 ? "regular" : $1.split(':').last
+          end
+        end
+      end
+
+      result :weights
+    end
+
+    # Element within list of fonts
+    class FontListElement < Scraper::Base
+      array :weights
+      array :charsets
+
+      attr_accessor :category # for storing serif, sans-serif, etc
+
+      # Font Name
+      process "div.preview span", :name => :text
+
+      # Weights
+      process "div.godesigner span.variantcount span", :weights_count => :text
+
+      # Families. Note, FamiliesCount will always be nil in the final output
+      # because the main extract method breaks down to specific fonts, rather
+      # than their meta-family grouping.
+      process "div.godesigner span.familycount span", :families_count => :text
+
+      # Designer name, but remove variants and families count text
+      process("div.godesigner", :designer => :text) do |el|
+        @designer = @designer.gsub(" #{@weights_count}&nbsp;variants", '')
+        @designer = @designer.gsub(" #{@families_count}&nbsp;families", '')
+
+        # remove font name from designer name
+        if @designer =~ /by (.*)/ then
+          @designer = $1
+        end
+      end
+
+      # Each listing has a small png image icon denoting its available character set.
+      process("div.ranges img", :charsets => "@src") do |el|
+        @charsets.each_with_index do |r, idx|
+          if r =~ /ic_(\w+)\.png/ then
+            @charsets[idx] = $1
+          end
+        end
+      end
+
+      result :designer, :name, :charsets, :weights_count, :weights, :families_count, :category
+    end
+
+
+    # Main list of fonts
+    class FontList < Scraper::Base
+      array :fonts
+      process "#fontlist li", :fonts => FontListElement
+      result :fonts
+    end
+  end
+end

data/lib/google_font_extractor.rb

@@ -0,0 +1,50 @@
+require 'tidy_ffi'
+require 'scrapi'
+
+require File.dirname(__FILE__) + '/extract.rb'
+
+
+module GoogleFontExtractor
+
+  CATEGORIES = %w(serif sans-serif display handwriting)
+
+  def self.fonts
+    # main list
+    final_font_list = []
+
+
+    CATEGORIES.each do |category|
+      # Get intermediate list of fonts
+      font_list = Extract::FontList.scrape(URI.parse("http://www.google.com/webfonts?sort=pop&category=#{category}"))
+
+
+      # Build final list of real fonts. Some fonts are listed are grouped by family on the main font 
+      # list, break those familiies down into individual fonts.
+      font_list.each_with_index do |font, idx|
+        if font.families_count then
+          Extract::FontList.scrape(URI.parse("http://www.google.com/webfonts/list?family=#{URI.encode(font.name)}&sort=pop&category=#{category}")).each do |intermediate|
+            intermediate[:category] = category
+            final_font_list << intermediate
+          end
+        else
+          font[:category] = category
+          final_font_list << font
+        end
+      end
+    end
+
+
+    # Tidy.
+    final_font_list.flatten!
+
+
+    # Further enhance final list of fonts with additional information from the individual font pages
+    # so we can provide information about the font weights (bold, etc) that are available.
+    final_font_list.each_with_index do |font, idx|
+      if font.weights_count then
+        font.weights = Extract::FontPage.scrape(URI.parse("http://www.google.com/webfonts/family?family=#{URI.encode(font.name)}"))
+      end
+    end
+  end
+
+end

data/lib/version.rb

@@ -0,0 +1,3 @@
+module GoogleFontExtractor
+  VERSION = '0.0.1'
+end

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification 
+name: google_font_extractor
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Jason Lambert
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-03-18 00:00:00 +00:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: tidy_ffi
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 1
+        - 3
+        version: 0.1.3
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: scrapi
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 2
+        - 0
+        - 0
+        version: 2.0.0
+  type: :runtime
+  version_requirements: *id002
+description: Extracts a list of all fonts available via the Google Webfonts API, including details of character sets supported, weights, and categorization.
+email: 
+- mail@jasonlambert.co.uk
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/extract.rb
+- lib/google_font_extractor.rb
+- lib/version.rb
+- README.md
+- google_font_extractor.gemspec
+has_rdoc: true
+homepage: https://github.com/mendable/google-font-extractor
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 1
+      - 3
+      - 6
+      version: 1.3.6
+requirements: []
+
+rubyforge_project: "[none]"
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Extracts a list of all fonts available via the Google Webfonts API
+test_files: []
+