Refactor PHP scraper with new initial_paths option

Thibaut committed 12 years ago

Commit b66d6d91 parent ca06cc72 files · +11 −18Browse files

Unified · Split

2 files

lib/docs/filters/php/entries.rb +1 −1
lib/docs/scrapers/php.rb +10 −17

@@ -106,7 +106,7 @@ module Docs · 105 unmodified lines
106	106	end
107	107
108	108	def include_default_entry?
109		− Php::INDEX_PATHS.exclude?(subpath) && doc.at_css('.reference', '.refentry', '.sect1')
	109	+ !initial_page? && doc.at_css('.reference', '.refentry', '.sect1')
110	110	end
111	111	end
112	112	end

lib/docs/scrapers/php.rb+10−17

@@ -5,18 +5,7 @@ module Docs · 4 unmodified lines
5	5	self.version = 'up to 5.5.6'
6	6	self.base_url = 'http://www.php.net/manual/en/'
7	7	self.root_path = 'index.html'
8		−
9		− # Downloaded from php.net/download-docs.php
10		− self.dir = '/Users/Thibaut/DevDocs/Docs/PHP'
11		−
12		− html_filters.push 'php/internal_urls', 'php/entries', 'php/clean_html', 'title'
13		− text_filters.push 'php/fix_urls'
14		−
15		− options[:title] = false
16		− options[:root_title] = 'PHP: Hypertext Preprocessor'
17		−
18		− INDEX_PATHS = %w(
19		− index.html
	8	+ self.initial_paths = %w(
20	9	funcref.html
21	10	refs.database.html
22	11	set.mysqlinfo.html
@@ -25,11 +14,15 @@ module Docs · 2 unmodified lines
25	14	reserved.interfaces.html
26	15	reserved.variables.html)
27	16
28		− options[:skip_links] = ->(filter) do
29		− INDEX_PATHS.exclude?(filter.subpath)
30		− end
	17	+ # Downloaded from php.net/download-docs.php
	18	+ self.dir = '/Users/Thibaut/DevDocs/Docs/PHP'
	19	+
	20	+ html_filters.push 'php/internal_urls', 'php/entries', 'php/clean_html', 'title'
	21	+ text_filters.push 'php/fix_urls'
31	22
32		− options[:only] = INDEX_PATHS.dup
	23	+ options[:title] = false
	24	+ options[:root_title] = 'PHP: Hypertext Preprocessor'
	25	+ options[:skip_links] = ->(filter) { !filter.initial_page? }
33	26
34	27	options[:only_patterns] = [
35	28	/\Aclass\./,
@@ -49,7 +42,7 @@ module Docs · 13 unmodified lines
49	42	sqlite3 sqlsrv ssh2 stats stream strings taint tidy uodbc url var varnish
50	43	xml xmlreader xmlrpc xmlwriter xsl yaf yaml zip zlib)
51	44
52		− options[:only].concat BOOKS.map { \|s\| "book.#{s}.html" }
	45	+ options[:only] = BOOKS.map { \|s\| "book.#{s}.html" }
53	46
54	47	options[:skip] = %w(
55	48	control-structures.intro.html