Finish scikit-image scraper

Thibaut Courouble committed 10 years ago

Commit 50f58321 parent 7f06c9c11 files · +30 −20Browse files

Unified · Split

11 files

Binary file not shown.

Binary file not shown.

@@ -1,7 +1,7 @@
1	[	1	[
2	[	2	[
3	"2016-09-05",	3	"2016-09-05",
4	"New documentations: <a href=\"/fish/\">Fish</a> and <a href=\"/bottle/\">Bottle</a>"	4	"New documentations: <a href=\"/fish/\">Fish</a>, <a href=\"/bottle/\">Bottle</a> and <a href=\"/scikit_image/\">scikit-image</a>"
5	], [	5	], [
6	"2016-08-07",	6	"2016-08-07",
7	"New documentation: <a href=\"/docker/\">Docker</a>"	7	"New documentation: <a href=\"/docker/\">Docker</a>"

     '2006-2016 Hampton Catlin, Nathan Weizenbaum, and Chris Eppstein',
     'MIT',
     'https://raw.githubusercontent.com/sass/sass/stable/MIT-LICENSE'
+  ], [
+    'scikit-image',
+    '2011 the scikit-image team',
+    'BSD',
+    'http://scikit-image.org/docs/dev/license.html'
   ], [
     'Sinon',
     '2010-2016 Christian Johansen',

@@ -117,6 +117,7 @@ · 116 unmodified lines
117	._icon-modernizr:before { background-position: -3rem -6rem; }	117	._icon-modernizr:before { background-position: -3rem -6rem; }
118	._icon-bower:before { background-position: -4rem -6rem; }	118	._icon-bower:before { background-position: -4rem -6rem; }
119	._icon-fish:before { background-position: -5rem -6rem; @extend %darkIconFix !optional; }	119	._icon-fish:before { background-position: -5rem -6rem; @extend %darkIconFix !optional; }
		120	._icon-scikit_image:before { background-position: -6rem -6rem; }
120	._icon-bottle:before { background-position: 0 -7rem; }	121	._icon-bottle:before { background-position: 0 -7rem; }
121	._icon-docker:before { background-position: -1rem -7rem; }	122	._icon-docker:before { background-position: -1rem -7rem; }
122	._icon-cakephp:before { background-position: -2rem -7rem; }	123	._icon-cakephp:before { background-position: -2rem -7rem; }

@@ -1,11 +0,0 @@
1	module Docs
2	class ScikitImage
3	class CleanHtmlFilter < Filter
4	def call
5	css('h2').remove
6	css('h1 + table').remove
7	doc
8	end
9	end
10	end
11	end

@@ -4,17 +4,27 @@ module Docs · 3 unmodified lines
4	def get_name	4	def get_name
5	name = at_css('h1').content.strip	5	name = at_css('h1').content.strip
6	name.remove! "\u{00b6}"	6	name.remove! "\u{00b6}"
7	name.remove! 'Module: '	7
8	name.remove! %r{ \(.*\)}	8	if slug.start_with?('api')
9	name.downcase!	9	name.remove! 'Module: '
		10	name.remove! %r{ \(.*\)}
		11	name.downcase!
		12	end
		13
10	name	14	name
11	end	15	end
12		16
13	def get_type	17	def get_type
14	name.split('.').first	18	if slug.start_with?('api')
		19	name.split('.').first
		20	else
		21	'Guide'
		22	end
15	end	23	end
16		24
17	def additional_entries	25	def additional_entries
		26	return [] unless slug.start_with?('api')
		27
18	entries = []	28	entries = []
19		29
20	css('.class > dt[id]', '.exception > dt[id]', '.attribute > dt[id]').each do \|node\|	30	css('.class > dt[id]', '.exception > dt[id]', '.attribute > dt[id]').each do \|node\|
@@ -30,8 +40,13 @@ module Docs · 9 unmodified lines
30	css('.function > dt[id]', '.method > dt[id]', '.classmethod > dt[id]').each do \|node\|	40	css('.function > dt[id]', '.method > dt[id]', '.classmethod > dt[id]').each do \|node\|
31	entries << [node['id'].remove('skimage.') + '()', node['id']]	41	entries << [node['id'].remove('skimage.') + '()', node['id']]
32	end	42	end
		43
33	entries	44	entries
34	end	45	end
		46
		47	def include_default_entry?
		48	slug != 'api/api'
		49	end
35	end	50	end
36	end	51	end
37	end	52	end

@@ -9,7 +9,7 @@ module Docs · 8 unmodified lines
9	node.remove	9	node.remove
10	end	10	end
11		11
12	css('em.xref', 'tt').each do \|node\|	12	css('em.xref', 'tt', 'cite').each do \|node\|
13	node.name = 'code'	13	node.name = 'code'
14	end	14	end
15		15

     self.name = 'scikit-image'
     self.slug = 'scikit_image'
     self.type = 'sphinx'
-    self.release = '0.12.2'
+    self.release = '0.12.3'
-    self.base_url = 'http://scikit-image.org/docs/0.12.x/api/'
+    self.base_url = 'http://scikit-image.org/docs/0.12.x/'
-    self.root_path = 'api.html'
     self.links = {
       home: 'http://scikit-image.org/',
       code: 'https://github.com/scikit-image/scikit-image'
     }
-    html_filters.push 'scikit_image/entries', 'scikit_image/clean_html', 'sphinx/clean_html'
+    html_filters.push 'scikit_image/entries', 'sphinx/clean_html'
     options[:container] = '.span9'
+    options[:skip] = %w(api_changes.html)
+    options[:only_patterns] = [/\Aapi/, /\Auser_guide/]
     options[:attribution] = <<-HTML
-      &copy; 2011 the scikit-image development team<br>
+      &copy; 2011 the scikit-image team<br>
-      Licensed under the scikit-image License.
+      Licensed under the BSD 3-clause License.
     HTML
   end
 end

Binary file not shown.

Binary file not shown.