History

Improve JavaScript scraper

Thibaut committed 11 years ago

Commit c5ace7e1 parent 0812ee03 files · +5 −3Browse files

Unified · Split

3 files
  1. lib/docs/filters/javascript/entries.rb +2 −2
  2. lib/docs/filters/mdn/clean_html.rb +1 −1
  3. lib/docs/scrapers/mdn/javascript.rb +2 −0
lib/docs/filters/javascript/entries.rb+2−2
@@ -8,14 +8,14 @@ module Docs · 7 unmodified lines
88
99 def get_name
1010 if slug.start_with? 'Global_Objects/'
11− name, method = *slug.sub('Global_Objects/', '').split('/')
11+ name, method, *rest = *slug.sub('Global_Objects/', '').split('/')
1212 name.prepend 'Intl.' if INTL_OBJECTS.include?(name)
1313
1414 if method
1515 unless method == method.upcase || method == 'NaN'
1616 method = method[0].downcase + method[1..-1] # e.g. Trim => trim
1717 end
18− name << ".#{method}"
18+ name << ".#{([method] + rest).join('.')}"
1919 end
2020
2121 name
lib/docs/filters/mdn/clean_html.rb+1−1
@@ -20,7 +20,7 @@ module Docs · 19 unmodified lines
2020 node.before(node.children).remove
2121 end
2222
23− css('h2[style]', 'pre[style]').remove_attr('style')
23+ css('h2[style]', 'pre[style]', 'th[style]', 'div[style*="line-height"]').remove_attr('style')
2424
2525 doc
2626 end
lib/docs/scrapers/mdn/javascript.rb+2−0
@@ -35,6 +35,8 @@ module Docs · 34 unmodified lines
3535 /Operators
3636 /Statements)
3737
38+ options[:skip_patterns] = [/additional_examples/i, /noSuchMethod/i]
39+
3840 options[:fix_urls] = ->(url) do
3941 url.sub! 'https://developer.mozilla.org/en-US/docs/JavaScript/Reference', Javascript.base_url
4042 url.sub! 'https://developer.mozilla.org/en/JavaScript/Reference', Javascript.base_url