Finish JSDoc scraper

Thibaut Courouble committed 8 years ago

Commit 8eb8a9e1 parent abbd43b12 files · +27 −62Browse files

Showing the changes to lib (3 of 12 files). Show all

Unified · Split

3 files

   class Jsdoc
     class CleanHtmlFilter < Filter
       def call
-        css('h2').each do |node|
+        at_css('h1').content = 'JSDoc' if root_page?
-          next unless node.content.strip == 'Table of Contents'
-          toc_ul = node.next_element
-          toc_block = node.add_next_sibling('<nav class="_toc" role="directory"></nav>').first
-          node.name = 'h3'
-          node['class'] = '_toc-title'
-          node.remove
-          toc_block.add_child(node)
-          toc_ul.remove
-          toc_ul['class'] = '_toc-list'
-          toc_ul.css('ul').each do |child_list|
-            child_list.remove
-          end
-          toc_block.add_child(toc_ul)
-        end
         css('.prettyprint').each do |node|
-          match = /lang-(\w+)/.match(node['class'])
+          node.content = node.content
-          next unless match
+          node['data-language'] = node['class'][/lang-(\w+)/, 1]
-          lang = match[1]
           node.remove_attribute('class')
-          node['data-language'] = lang
         end
-        css('figure').each do |node|
+        css('figcaption').each do |node|
-          caption = node.at_css 'figcaption'
+          node.name = 'div'
-          next unless caption
+          node['class'] = '_pre-heading'
+        end
-          node.children.last.add_next_sibling(caption)
+        css('figure').each do |node|
+          node.before(node.children).remove
         end
         doc

   class Jsdoc
     class EntriesFilter < Docs::EntriesFilter
       def get_name
-        at_css('h1').content
+        name = at_css('h1').content
+        name.prepend 'JSDoc: ' if !name.include?('@') && !name.include?('JSDoc')
+        name
       end
       def get_type
         case slug
           when /^about-/
           when /^tags-/
             'Tags'
           else
-            'Other' # Only shown if a new category gets added in the upstream docs
+            'Miscellaneous' # Only shown if a new category gets added in the upstream docs
         end
       end
     end

 module Docs
   class Jsdoc < UrlScraper
     self.name = 'JSDoc'
-    self.type = 'jsdoc'
+    self.type = 'simple'
     self.release = '3.5.5'
     self.base_url = 'http://usejsdoc.org/'
+    self.root_path = 'index.html'
     self.links = {
       home: 'http://usejsdoc.org/',
       code: 'https://github.com/jsdoc3/jsdoc'
       'about-license-jsdoc3.html'
     ]
     options[:attribution] = <<-HTML
-      &copy; 2011&ndash;2017
+      &copy; 2011&ndash;2017 the contributors to the JSDoc 3 documentation project<br>
-        <a href="https://github.com/jsdoc3/jsdoc3.github.com/contributors">
+      Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0.
-          JSDoc 3 contributors
-        </a><br>
-      Licensed under
-        <a href="http://creativecommons.org/licenses/by-sa/3.0/">
-          CC BY-SA 3.0
-        </a>
     HTML
   end
 end