History

mdn: update scraper to mdn/yari

Simon Legner committed 5 years ago

Commit 4dc95571 parent 92d8a8e4 files · +18 −12Browse files

Unified · Split

4 files
  1. assets/stylesheets/pages/_mdn.scss +1 −0
  2. lib/docs/filters/mdn/clean_html.rb +15 −0
  3. lib/docs/filters/svg/clean_html.rb +1 −1
  4. lib/docs/scrapers/mdn/mdn.rb +1 −11
assets/stylesheets/pages/_mdn.scss+1−0
@@ -27,6 +27,7 @@ · 26 unmodified lines
2727 p > code, li > code { @extend %label; }
2828
2929 > .note,
30+ .notecard, // MDN 2021
3031 .notice,
3132 .warning,
3233 .overheadIndicator,
lib/docs/filters/mdn/clean_html.rb+15−0
@@ -41,6 +41,18 @@ module Docs · 40 unmodified lines
4141 node.parent['id'] = node['name']
4242 node.before(node.content).remove
4343 end
44+ css('h2 > a, h3 > a').each do |node|
45+ node.parent.content = node.content
46+ end
47+
48+ css('.notecard > h4').each do |node|
49+ node.name = 'strong'
50+ end
51+
52+ css('svg.deprecated').each do |node|
53+ node.name = 'span'
54+ node.content = node.content
55+ end
4456
4557 css('dt > a[id]').each do |node|
4658 next if node['href']
@@ -64,6 +76,9 @@ module Docs · 17 unmodified lines
6476 end
6577
6678 # New compatibility tables
79+ # FIXME(2021):
80+ # - fetched from external JSON: https://developer.mozilla.org/en-US/docs/Web/SVG/Attribute/alignment-baseline/bcd.json
81+ # - https://github.com/mdn/yari/blob/master/build/bcd-urls.js
6782
6883 css('.bc-data #Legend + dl', '.bc-data #Legend', '.bc-data #Legend_2 + dl', '.bc-data #Legend_2', '.bc-browser-name').remove
6984
lib/docs/filters/svg/clean_html.rb+1−1
@@ -11,7 +11,7 @@ module Docs · 10 unmodified lines
1111 end
1212
1313 def other
14− css('.prevnext').remove
14+ css('.prev-next').remove
1515
1616 if at_css('p').content.include?("\u{00AB}")
1717 at_css('p').remove
lib/docs/scrapers/mdn/mdn.rb+1−11
@@ -3,12 +3,9 @@ module Docs · 2 unmodified lines
33 self.abstract = true
44 self.type = 'mdn'
55
6− params[:raw] = 1
7− params[:macros] = 1
8−
96 html_filters.push 'mdn/clean_html'
107
11− options[:rate_limit] = 200
8+ options[:container] = '#content'
129 options[:trailing_slash] = false
1310
1411 options[:skip_link] = ->(link) {
@@ -23,12 +20,5 @@ module Docs · 8 unmodified lines
2320 def get_latest_version(opts)
2421 get_latest_github_commit_date('mdn', 'content', opts)
2522 end
26−
27− private
28−
29− def process_response?(response)
30− response.effective_url.host = 'developer.mozilla.org' if response.effective_url.host == 'wiki.developer.mozilla.org'
31− super && response.effective_url.query == 'raw=1&macros=1'
32− end
3323 end
3424 end