[pull] main from freeCodeCamp:main

lib/docs/filters/homebrew/entries.rb

@@ -3,8 +3,20 @@ class Homebrew
     class EntriesFilter < Docs::EntriesFilter
       def get_name
         header = at_css('h1')
-        name = header.nil? ? current_url.normalized_path[1..-1].gsub(/-/, ' ') : header.content.strip
-        name.remove! %r{\(.*}
+
+        if current_url.path.start_with?('/rubydoc')
+          # Titles in rubydoc content follow a different format, with a bit of cleanup needed.
+          name = header
+            .content
+            .gsub('Class: ', '')
+            .gsub('Module: ', '')
+            .gsub('Exception: ', '')
+            .gsub(' Private', '')
+        else
+          name = header.nil? ? current_url.normalized_path[1..-1].gsub(/-/, ' ') : header.content.strip
+          name.remove! %r{\(.*}
+        end
+
         name
       end
 
@@ -26,13 +38,21 @@ def get_name
         Building-Against-Non-Homebrew-Dependencies
         How-to-Create-and-Maintain-a-Tap
         Brew-Test-Bot
-        Prose-Style-Guidelines
         Typechecking
         Reproducible-Builds
       )
 
       def get_type
-        if CONTRIBUTOR_SLUGS.include?(slug)
+        if current_url.path.start_with?('/rubydoc')
+          header = at_css('h1').content
+          if header.start_with?('Module')
+            'API Modules'
+          elsif header.start_with?('Class')
+            'API Classes'
+          else
+            'API Exceptions'
+          end
+        elsif CONTRIBUTOR_SLUGS.include?(slug)
           'Contributors'
         else
           'Users'

lib/docs/scrapers/haskell.rb

@@ -78,10 +78,9 @@ class Haskell < UrlScraper
     end
 
     def get_latest_version(opts)
-      doc = fetch_doc('https://www.haskell.org/ghc/download.html', opts)
-      links = doc.css('a').to_a
-      versions = links.map {|link| link.content.scan(/\A([0-9.]+)\Z/)}
-      versions.find {|version| !version.empty?}[0][0]
+      tags = get_github_tags('ghc', 'ghc', opts)
+      tag = tags.find {|t| t['name'].ends_with?('-release') }['name']
+      tag[/ghc-(.*)-release/, 1]
     end
 
   end

lib/docs/scrapers/homebrew.rb

@@ -1,8 +1,10 @@
 module Docs
   class Homebrew < UrlScraper
+    # include MultipleBaseUrls
+
     self.name = 'Homebrew'
     self.type = 'simple'
-    self.release = '4.6.15'
+    self.release = '6.0.3'
     self.base_url = 'https://docs.brew.sh/'
     self.links = {
       home: 'https://brew.sh',
@@ -11,9 +13,29 @@ class Homebrew < UrlScraper
 
     html_filters.push 'homebrew/entries', 'homebrew/clean_html'
 
-    options[:container] = ->(filter) { filter.root_page? ? '#home' : '#page' }
+    options[:container] = ->(filter) do
+      if filter.current_url.path.include?('rubydoc')
+        '#content'
+      else
+        '#default'
+      end
+    end
 
-    options[:skip_patterns] = [/maintainer/i, /core\-contributor/i, /kickstarter/i, /governance/i]
+    # Mostly handbook articles with no code.
+    options[:skip_patterns] = [
+      /maintainer/i,
+      /core\-contributor/i,
+      /kickstarter/i,
+      /governance/i,
+      /responsible/i,
+      /leadership/i,
+      /prose/i,
+      /expense/i,
+      /creating-a-homebrew-issue/i,
+      /homebrew-and-java/i,
+      /checksum_deprecation/i,
+      /Working-with/i
+    ]
 
     options[:attribution] = <<-HTML
       &copy; 2009&ndash;present Homebrew contributors<br>

lib/docs/scrapers/love.rb

@@ -43,8 +43,7 @@ class Love < UrlScraper
     HTML
 
     def get_latest_version(opts)
-      doc = fetch_doc('https://love2d.org/wiki/Version_History', opts)
-      doc.at_css('#mw-content-text table a').content
+      get_github_tags('love2d', 'love', opts).first['name']
     end
   end
 end

lib/docs/scrapers/mongoose.rb

@@ -29,9 +29,7 @@ class Mongoose < UrlScraper
     HTML
 
     def get_latest_version(opts)
-      doc = fetch_doc('https://mongoosejs.com/docs/', opts)
-      label = doc.at_css('.pure-menu-link').content.strip
-      label.sub(/Version /, '')
+      get_github_tags('Automattic', 'mongoose', opts).find {|t| t['name'].starts_with?(/\d/)}['name']
     end
   end
 end

lib/docs/scrapers/python.rb

@@ -15,6 +15,7 @@ class Python < UrlScraper
 
     options[:skip_patterns] = [/whatsnew/]
     options[:skip] = %w(
+      archives/
       library/2to3.html
       library/formatter.html
       library/intro.html
@@ -28,7 +29,7 @@ class Python < UrlScraper
     HTML
 
     version '3.14' do
-      self.release = '3.14.4'
+      self.release = '3.14.6'
       self.base_url = "https://docs.python.org/#{self.version}/"
 
       html_filters.push 'python/entries_v3', 'sphinx/clean_html', 'python/clean_html'

lib/docs/scrapers/tensorflow/tensorflow.rb

@@ -45,8 +45,8 @@ class Tensorflow < UrlScraper
     end
 
     def get_latest_version(opts)
-      doc = fetch_doc(self.base_url, opts)
-      doc.title[/TensorFlow v([.\d]+)/, 1]
+      tag = get_github_tags('tensorflow', 'tensorflow', opts).find { |t| !t['name'].include?('-rc') }
+      tag['name'][1..-1]
     end
 
     private

lib/docs/scrapers/threejs.rb

@@ -44,17 +44,17 @@ class Threejs < UrlScraper
     self.base_url = "https://threejs.org/docs"
 
     def get_latest_version(opts)
-      get_latest_github_release('mrdoob', 'three.js', opts)[1..]
+      get_github_tags('mrdoob', 'three.js', opts).first['name'][1..]
     end
 
     def initial_paths
       paths = []
-      url = 'https://threejs.org/docs/list.json'
+      url = 'https://threejs.org/docs/search.json'
       response = Request.run(url)
       json_data = JSON.parse(response.body)
 
       # Process both API and manual sections
-      process_documentation(json_data['en'], paths)
+      process_documentation(json_data, paths)
       paths
     end
 
@@ -78,4 +78,4 @@ def process_documentation(data, paths, prefix = '')
       end
     end
   end
-end 
+end