scrappy 0.1.8 → 0.1.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/History.txt +5 -0
- data/lib/scrappy.rb +1 -1
- data/lib/scrappy/agent/extractor.rb +1 -1
- data/lib/scrappy/selectors/new_uri.rb +1 -1
- data/scrappy.gemspec +2 -2
- metadata +3 -3
data/History.txt
CHANGED
data/lib/scrappy.rb
CHANGED
@@ -6,7 +6,7 @@ module Scrappy
|
|
6
6
|
triples = []
|
7
7
|
content = Nokogiri::HTML(html, nil, 'utf-8')
|
8
8
|
|
9
|
-
uri_selectors = kb.find(nil, Node('rdf:type'), Node('sc:UriSelector')) + kb.find(nil, Node('rdf:type'), Node('sc:UriPatternSelector')).flatten.select do |uri_selector|
|
9
|
+
uri_selectors = (kb.find(nil, Node('rdf:type'), Node('sc:UriSelector')) + kb.find(nil, Node('rdf:type'), Node('sc:UriPatternSelector'))).flatten.select do |uri_selector|
|
10
10
|
class_name = uri_selector.rdf::type.first.to_s.split('#').last
|
11
11
|
results = Kernel.const_get(class_name).filter uri_selector, {:content=>content, :uri=>uri}
|
12
12
|
!results.empty?
|
@@ -8,7 +8,7 @@ module NewUriSelector
|
|
8
8
|
end
|
9
9
|
|
10
10
|
contents.map do |content|
|
11
|
-
new_uri = selector.sc::prefix.to_s + content.wikify
|
11
|
+
new_uri = selector.sc::prefix.first.to_s + content.wikify + selector.sc::suffix.first.to_s
|
12
12
|
{ :uri=>new_uri, :content=>doc[:content], :value=>new_uri }
|
13
13
|
end
|
14
14
|
end
|
data/scrappy.gemspec
CHANGED
@@ -2,11 +2,11 @@
|
|
2
2
|
|
3
3
|
Gem::Specification.new do |s|
|
4
4
|
s.name = %q{scrappy}
|
5
|
-
s.version = "0.1.
|
5
|
+
s.version = "0.1.9"
|
6
6
|
|
7
7
|
s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
|
8
8
|
s.authors = ["Jose Ignacio"]
|
9
|
-
s.date = %q{2010-12-
|
9
|
+
s.date = %q{2010-12-16}
|
10
10
|
s.default_executable = %q{scrappy}
|
11
11
|
s.description = %q{RDF web scraper}
|
12
12
|
s.email = %q{joseignacio.fernandez@gmail.com}
|
metadata
CHANGED
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 1
|
8
|
-
-
|
9
|
-
version: 0.1.
|
8
|
+
- 9
|
9
|
+
version: 0.1.9
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
12
|
- Jose Ignacio
|
@@ -14,7 +14,7 @@ autorequire:
|
|
14
14
|
bindir: bin
|
15
15
|
cert_chain: []
|
16
16
|
|
17
|
-
date: 2010-12-
|
17
|
+
date: 2010-12-16 00:00:00 +01:00
|
18
18
|
default_executable:
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|