History

Improve GitHub scraper

Thibaut Courouble committed 9 years ago

Commit 85fffdc1 parent 80cc88c4 files · +10 −10Browse files

Unified · Split

4 files
  1. assets/javascripts/views/pages/github.coffee +0 −9
  2. assets/javascripts/views/pages/simple.coffee +1 −0
  3. lib/docs/filters/github/clean_html.rb +5 −1
  4. lib/docs/filters/nginx_lua_module/clean_html.rb +4 −0
assets/javascripts/views/pages/github.coffee+0−9
@@ -1,9 +0,0 @@
1−#= require views/pages/base
2−
3−class app.views.GithubPage extends app.views.BasePage
4− LANGUAGE_RGX = /highlight-source-(\w+)/
5−
6− prepare: ->
7− for el in @findAll('pre.highlight')
8− @highlightCode(el, el.className.match(LANGUAGE_RGX)[1])
9− return
assets/javascripts/views/pages/simple.coffee+1−0
@@ -28,6 +28,7 @@ app.views.EmberPage = · 27 unmodified lines
2828 app.views.ErlangPage =
2929 app.views.ExpressPage =
3030 app.views.FlowPage =
31+app.views.GithubPage =
3132 app.views.GoPage =
3233 app.views.ImmutablePage =
3334 app.views.InfluxdataPage =
lib/docs/filters/github/clean_html.rb+5−1
@@ -8,11 +8,15 @@ module Docs · 7 unmodified lines
88 end
99
1010 css('.highlight > pre').each do |node|
11− node['class'] = node.parent['class']
11+ node['data-language'] = node.parent['class'][/highlight-source-(\w+)/, 1]
1212 node.content = node.content.strip_heredoc.gsub(' ', ' ')
1313 node.parent.replace(node)
1414 end
1515
16+ css('pre > code').each do |node|
17+ node.before(node.children).remove
18+ end
19+
1620 doc
1721 end
1822 end
lib/docs/filters/nginx_lua_module/clean_html.rb+4−0
@@ -8,6 +8,10 @@ module Docs · 7 unmodified lines
88 node.name = node.name.sub(/\d/) { |i| i.to_i + 1 }
99 end
1010
11+ css('a > img').each do |node|
12+ node.parent.before(node.parent.children).remove
13+ end
14+
1115 doc
1216 end
1317 end