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
8 8
9 def get_name9 def get_name
10 if slug.start_with? 'Global_Objects/'10 if slug.start_with? 'Global_Objects/'
11 name, method = *slug.sub('Global_Objects/', '').split('/')11 name, method, *rest = *slug.sub('Global_Objects/', '').split('/')
12 name.prepend 'Intl.' if INTL_OBJECTS.include?(name)12 name.prepend 'Intl.' if INTL_OBJECTS.include?(name)
13 13
14 if method14 if method
15 unless method == method.upcase || method == 'NaN'15 unless method == method.upcase || method == 'NaN'
16 method = method[0].downcase + method[1..-1] # e.g. Trim => trim16 method = method[0].downcase + method[1..-1] # e.g. Trim => trim
17 end17 end
18 name << ".#{method}"18 name << ".#{([method] + rest).join('.')}"
19 end19 end
20 20
21 name21 name
lib/docs/filters/mdn/clean_html.rb+1−1
@@ -20,7 +20,7 @@ module Docs · 19 unmodified lines
20 node.before(node.children).remove20 node.before(node.children).remove
21 end21 end
22 22
23 css('h2[style]', 'pre[style]').remove_attr('style')23 css('h2[style]', 'pre[style]', 'th[style]', 'div[style*="line-height"]').remove_attr('style')
24 24
25 doc25 doc
26 end26 end
lib/docs/scrapers/mdn/javascript.rb+2−0
@@ -35,6 +35,8 @@ module Docs · 34 unmodified lines
35 /Operators35 /Operators
36 /Statements)36 /Statements)
37 37
38 options[:skip_patterns] = [/additional_examples/i, /noSuchMethod/i]
39
38 options[:fix_urls] = ->(url) do40 options[:fix_urls] = ->(url) do
39 url.sub! 'https://developer.mozilla.org/en-US/docs/JavaScript/Reference', Javascript.base_url41 url.sub! 'https://developer.mozilla.org/en-US/docs/JavaScript/Reference', Javascript.base_url
40 url.sub! 'https://developer.mozilla.org/en/JavaScript/Reference', Javascript.base_url42 url.sub! 'https://developer.mozilla.org/en/JavaScript/Reference', Javascript.base_url