Finish Bluebird scraper

Thibaut Courouble committed 8 years ago

Commit dac41921 parent b399a0c10 files · +47 −30Browse files

Unified · Split

10 files

Binary file not shown.

Binary file not shown.

@@ -1,5 +1,8 @@
1	1	[
2	2	[
	3	+ "2017-11-26",
	4	+ "New documentation: <a href=\"/bluebird/\">Bluebird</a>"
	5	+ ], [
3	6	"2017-11-18",
4	7	"Added print & PDF stylesheet.\nFeedback welcome on <a href=\"https://twitter.com/DevDocs\" target=\"_blank\" rel=\"noopener\">Twitter</a> and <a href=\"https://github.com/Thibaut/devdocs\" target=\"_blank\" rel=\"noopener\">GitHub</a>."
5	8	], [

@@ -112,6 +112,11 @@ credits = [ · 111 unmodified lines
112	112	'2010-2016 Jeremy Ashkenas, DocumentCloud',
113	113	'MIT',
114	114	'https://raw.githubusercontent.com/jashkenas/backbone/master/LICENSE'
	115	+ ], [
	116	+ 'Bluebird',
	117	+ '2013-2017 Petka Antonov',
	118	+ 'MIT',
	119	+ 'https://raw.githubusercontent.com/petkaantonov/bluebird/master/LICENSE'
115	120	], [
116	121	'Bootstrap',
117	122	'2011-2017 Twitter, Inc.<br>2011-2017 The Bootstrap Authors',

@@ -164,3 +164,4 @@ · 163 unmodified lines
164	164	._icon-nim:before { background-position: -5rem -2rem; @extend %doc-icon-2; @extend %darkIconFix !optional; }
165	165	._icon-vulkan:before { background-position: -6rem -2rem; @extend %doc-icon-2; @extend %darkIconFix !optional; }
166	166	._icon-d:before { background-position: -7rem -2rem; @extend %doc-icon-2; }
	167	+._icon-bluebird:before { background-position: -8rem -2rem; @extend %doc-icon-2; }

@@ -2,8 +2,33 @@ module Docs · 1 unmodified line
2	2	class Bluebird
3	3	class CleanHtmlFilter < Filter
4	4	def call
5		− css('.post-content > p:first').remove
6		− css('pre').attr('data-language', 'javascript')
	5	+ @doc = at_css('.post')
	6	+
	7	+ css('hr').remove
	8	+
	9	+ css('.api-code-section').each do \|node\|
	10	+ node.previous_element.remove
	11	+ end
	12	+
	13	+ css('.post-header', '.post-content', '.api-reference-menu', '.api-code-section', 'markdown', '.highlight', 'code code').each do \|node\|
	14	+ node.before(node.children).remove
	15	+ end
	16	+
	17	+ at_css('> h2:first-child').name = 'h1' unless at_css('h1')
	18	+
	19	+ css('.header-anchor[name]').each do \|node\|
	20	+ node.parent['id'] = node['name']
	21	+ end
	22	+
	23	+ css('pre').each do \|node\|
	24	+ node.content = node.content
	25	+ node['data-language'] = 'javascript'
	26	+ end
	27	+
	28	+ css('.info-box').each do \|node\|
	29	+ node.name = 'blockquote'
	30	+ end
	31	+
7	32	doc
8	33	end
9	34	end

@@ -26,41 +26,23 @@ module Docs · 25 unmodified lines
26	26	done promise.config suppressunhandledrejections
27	27	promise.onpossiblyunhandledrejection promise.bind
28	28	promise.onunhandledrejectionhandled),
29		− 'Progression migration': %(),
30		− 'Deferred migration': %(),
31		− 'Environment variables': %(),
32		− "Beginner's Guide": %w(),
33		− 'Error management configuration': %w(),
34		− 'Anti-patterns': %w(),
35		− 'Deprecated APIs': %w()
36	29	}
37	30
38	31	def get_name
39		− name = at_css('h1.post-title')
40		− if name.nil?
41		− name = at_css('.post-content h2')
42		− end
43		− name.text
	32	+ name = at_css('h1').content.strip
	33	+ name << '()' if doc.to_html.include?("#{name}(")
	34	+ name
44	35	end
45	36
46	37	def get_type
47		− type = nil
48		− TYPE_MAP.each do \|k,v\|
49		− if k.to_s.casecmp(name.strip) == 0
50		− type = k
51		− break
52		− else
53		− slug_end = slug.sub(%r(^docs/api/), '')
54		− if v.include?(slug_end.downcase)
55		− type = k
56		− break
57		− end
	38	+ if slug.start_with?('api')
	39	+ TYPE_MAP.each do \|key, value\|
	40	+ return key.to_s if value.include?(slug.remove('api/'))
58	41	end
	42	+ else
	43	+ 'Guides'
59	44	end
60		−
61		− type.to_s
62	45	end
63		−
64	46	end
65	47	end
66	48	end

@@ -1,9 +1,10 @@
1	1	module Docs
2	2	class Bluebird < UrlScraper
3		− self.type = 'bluebird'
4		− self.base_url = 'http://bluebirdjs.com'
5		− self.root_path = '/docs/api-reference.html'
6		− self.release = '3.5.0'
	3	+ self.type = 'simple'
	4	+ self.release = '3.5.1'
	5	+ self.base_url = 'http://bluebirdjs.com/docs/'
	6	+ self.root_path = 'api-reference.html'
	7	+ self.force_gzip = true
7	8	self.links = {
8	9	home: 'http://bluebirdjs.com/',
9	10	code: 'https://github.com/petkaantonov/bluebird/'
@@ -11,10 +12,10 @@ module Docs · 1 unmodified line
11	12
12	13	html_filters.push 'bluebird/clean_html', 'bluebird/entries'
13	14
14		− options[:container] = 'body .post'
	15	+ options[:skip] = %w(support.html download-api-reference.html contribute.html)
15	16
16	17	options[:attribution] = <<-HTML
17		− © Petka Antonov<br/>
	18	+ © 2013–2017 Petka Antonov<br>
18	19	Licensed under the MIT License.
19	20	HTML
20	21	end

Binary file not shown.

Binary file not shown.