Update Less scraper (1.6.3)

Thibaut committed 12 years ago

Commit b035be31 parent bc95cfd5 files · +74 −73Browse files

Showing the changes to lib/docs (3 of 5 files). Show all

Unified · Split

3 files

lib/docs/filters/less/clean_html.rb +11 −22
lib/docs/filters/less/entries.rb +46 −33
lib/docs/scrapers/less.rb +10 −7

lib/docs/filters/less/clean_html.rb+11−22

   class Less
     class CleanHtmlFilter < Filter
       def call
-        # Remove everything but language and function reference
+        css('.source-link').remove
-        doc.children = css('#docs', '#reference').children
-        # Change headings
+        css('#functions-overview').each do |node|
-        css('h1', 'h2', 'h3').each do |node|
+          node.ancestors('.docs-section').remove
-          node.name = "h#{node.name.last.to_i + 1}"
-          node['id'] ||= node.content.strip.parameterize
         end
-        # Remove .content div
+        css('.docs-section', 'blockquote').each do |node|
-        css('.content').each do |node|
+          node.before(node.children).remove
-          node.before(node.elements)
-          node.remove
         end
-        # Remove function index
+        css('.page-header').each do |node|
-        css('#function-reference').each do |node|
+          node.before(node.first_element_child).remove
-          while node.next.content.strip != 'String functions'
-            node.next.remove
-          end
         end
-        # Remove duplicates
+        css('h1, h2, h3, h4').each do |node|
-        [css('[id="unit"]').last, css('[id="color"]').last].each do |node|
+          node.name = node.name.sub(/\d/) { |i| i.to_i + 1 }
-          node.next.remove while %w(h2 h3 h4).exclude?(node.next.name)
-          node.remove
         end
-        # Differentiate function headings
+        css('pre').each do |node|
-        css('#function-reference ~ h4').each do |node|
+          node.content = node.content
-          node['class'] = 'function'
         end
         doc

lib/docs/filters/less/entries.rb+46−33

@@ -1,48 +1,61 @@
1	module Docs	1	module Docs
2	class Less	2	class Less
3	class EntriesFilter < Docs::EntriesFilter	3	class EntriesFilter < Docs::EntriesFilter
4	SKIP_NAMES = ['Parametric Mixins', 'Mixins With Multiple Parameters',	4	def name
5	'Return Values', 'Unlocking Mixins', 'Media Queries as Variables']	5	at_css('h1').content
6		6	end
7	REPLACE_NAMES = {	7
8	'The @arguments variable' => '@arguments',	8	def type
9	'Advanced arguments and the @rest variable' => '@rest',	9	root_page? ? 'Language' : nil
10	'The Keyword !important' => '!important',
11	'Pattern-matching and Guard expressions' => 'Pattern-matching',
12	'Advanced Usage of &' => '&',
13	'Importing' => '@import',
14	'JavaScript evaluation' => 'JavaScript',
15	'% format' => '%'
16	}
17
18	def include_default_entry?
19	false
20	end	10	end
21		11
22	def additional_entries	12	def additional_entries
		13	root_page? ? language_entries : function_entries
		14	end
		15
		16	def language_entries
23	entries = []	17	entries = []
24	type = ''
25
26	css('> [id]').each do \|node\|
27	if node.name == 'h2'
28	type = node.content.strip
29	type.sub! 'The Language', 'Language'
30	type.sub! 'functions', 'Functions'
31	next
32	end
33		18
34	# Skip function categories (e.g. "Color definition")	19	css('h1').each do \|node\|
35	next if node.name == 'h3' && type != 'Language'	20	name = node.content
		21	entries << [name, node['id']] unless name == 'Overview'
		22	end
		23
		24	css('h2[id^="import-options-"]').each do \|node\|
		25	entries << ["@import #{node.content}", node['id']]
		26	end
36		27
37	name = node.content.strip	28	entries.concat [
		29	['@var', 'variables-feature'],
		30	['@{} interpolation', 'variables-feature-variable-interpolation'],
		31	['url()', 'variables-feature-urls'],
		32	['@property', 'variables-feature-properties'],
		33	['@@var', 'variables-feature-variable-names'],
		34	[':extend()', 'extend-feature'],
		35	[':extend(all)', 'extend-feature-extend-quotallquot'],
		36	['@arguments', 'mixins-parametric-feature-the-codeargumentscode-variable'],
		37	['@rest', 'mixins-parametric-feature-advanced-arguments-and-the-coderestcode-variable'],
		38	['@import', 'import-directives-feature'],
		39	['when', 'mixin-guards-feature'],
		40	['.loop()', 'loops-feature'],
		41	['+:', 'merge-feature'] ]
38		42
39	next if SKIP_NAMES.include?(name)	43	entries
		44	end
40		45
41	name = REPLACE_NAMES[name] if REPLACE_NAMES[name]	46	def function_entries
42	name.gsub!(/ [A-Z]/) { \|str\| str.downcase! }	47	entries = []
		48	type = nil
43		49
44	entries << ['~', node['id'], type] if name == 'e'	50	css('.docs-section').each do \|section\|
45	entries << [name, node['id'], type]	51	if title = section.at_css('h1')
		52	type = title.content
		53	type.sub! %r{(\w+) Functions}, 'Functions: \1'
		54	end
		55
		56	section.css('h3').each do \|node\|
		57	entries << [node.content, node['id'], type]
		58	end
46	end	59	end
47		60
48	entries	61	entries

lib/docs/scrapers/less.rb+10−7

 module Docs
   class Less < UrlScraper
     self.type = 'less'
-    self.version = '1.6.0'
+    self.version = '1.6.3'
     self.base_url = 'http://lesscss.org'
+    self.root_path = '/features'
+    self.initial_paths = %w(/functions)
-    html_filters.push 'less/clean_html', 'less/entries', 'title'
+    html_filters.push 'less/entries', 'less/clean_html', 'title'
-    options[:title] = 'LESS'
+    options[:title] = 'Less'
-    options[:container] = 'section'
+    options[:container] = 'div[role=main]'
-    options[:skip_links] = true
+    options[:follow_links] = false
+    options[:trailing_slash] = false
     options[:attribution] = <<-HTML
-      &copy; 2009&ndash;2014 Alexis Sellier &amp; The Core Less Team<br>
+      &copy; 2009&ndash;2014 The Core Less Team<br>
-      Licensed under the Apache License v2.0.
+      Licensed under the Creative Commons Attribution License 3.0.
     HTML
   end
 end