scrappy 0.1.19 → 0.1.20
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/Rakefile +1 -1
- data/lib/scrappy.rb +1 -1
- data/lib/scrappy/selectors/new_uri.rb +9 -1
- data/scrappy.gemspec +5 -2
- metadata +17 -3
data/History.txt
CHANGED
data/Rakefile
CHANGED
@@ -11,7 +11,7 @@ Echoe.new('scrappy', Scrappy::VERSION) do |p|
|
|
11
11
|
p.email = "joseignacio.fernandez@gmail.com"
|
12
12
|
p.install_message = '**(Optional) Remember to install rbwebkitgtk for visual parsing features**'
|
13
13
|
p.ignore_pattern = ["pkg/*"]
|
14
|
-
p.dependencies = [['activesupport','>= 2.3.5'], ['sinatra', '>= 1.1.2'], ['thin', '>= 1.2.7'], ['nokogiri', '>= 1.4.1'], ['mechanize','>= 1.0.0'], ['lightrdf','>= 0.1.9'], ['i18n', '>= 0.4.2']]
|
14
|
+
p.dependencies = [['activesupport','>= 2.3.5'], ['sinatra', '>= 1.1.2'], ['thin', '>= 1.2.7'], ['nokogiri', '>= 1.4.1'], ['mechanize','>= 1.0.0'], ['lightrdf','>= 0.1.9'], ['i18n', '>= 0.4.2'], ['haml', '>= 3.0.24']]
|
15
15
|
end
|
16
16
|
|
17
17
|
Rake::RDocTask.new(:rdoc) do |rdoc|
|
data/lib/scrappy.rb
CHANGED
@@ -7,8 +7,16 @@ module NewUriSelector
|
|
7
7
|
[ doc[:content].text ]
|
8
8
|
end
|
9
9
|
|
10
|
+
@@indexes ||= Hash.new(0)
|
11
|
+
prefix = selector.sc::prefix.first.to_s
|
12
|
+
prefix = (prefix =~ /\Ahttp/ ? URI::parse(doc[:uri]).merge(prefix).to_s : "#{doc[:uri]}#{prefix}")
|
13
|
+
suffix = selector.sc::suffix.first.to_s
|
14
|
+
|
10
15
|
contents.map do |content|
|
11
|
-
|
16
|
+
variable = selector.sc::sequence.first.to_s=="true" ? (@@indexes[selector] += 1) : content.wikify
|
17
|
+
|
18
|
+
new_uri = "#{prefix}#{variable}#{suffix}"
|
19
|
+
|
12
20
|
{ :uri=>new_uri, :content=>doc[:content], :value=>new_uri }
|
13
21
|
end
|
14
22
|
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 = "0.1.20"
|
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{2011-02-
|
9
|
+
s.date = %q{2011-02-25}
|
10
10
|
s.default_executable = %q{scrappy}
|
11
11
|
s.description = %q{RDF web scraper}
|
12
12
|
s.email = %q{joseignacio.fernandez@gmail.com}
|
@@ -34,6 +34,7 @@ Gem::Specification.new do |s|
|
|
34
34
|
s.add_runtime_dependency(%q<mechanize>, [">= 1.0.0"])
|
35
35
|
s.add_runtime_dependency(%q<lightrdf>, [">= 0.1.9"])
|
36
36
|
s.add_runtime_dependency(%q<i18n>, [">= 0.4.2"])
|
37
|
+
s.add_runtime_dependency(%q<haml>, [">= 3.0.24"])
|
37
38
|
else
|
38
39
|
s.add_dependency(%q<activesupport>, [">= 2.3.5"])
|
39
40
|
s.add_dependency(%q<sinatra>, [">= 1.1.2"])
|
@@ -42,6 +43,7 @@ Gem::Specification.new do |s|
|
|
42
43
|
s.add_dependency(%q<mechanize>, [">= 1.0.0"])
|
43
44
|
s.add_dependency(%q<lightrdf>, [">= 0.1.9"])
|
44
45
|
s.add_dependency(%q<i18n>, [">= 0.4.2"])
|
46
|
+
s.add_dependency(%q<haml>, [">= 3.0.24"])
|
45
47
|
end
|
46
48
|
else
|
47
49
|
s.add_dependency(%q<activesupport>, [">= 2.3.5"])
|
@@ -51,5 +53,6 @@ Gem::Specification.new do |s|
|
|
51
53
|
s.add_dependency(%q<mechanize>, [">= 1.0.0"])
|
52
54
|
s.add_dependency(%q<lightrdf>, [">= 0.1.9"])
|
53
55
|
s.add_dependency(%q<i18n>, [">= 0.4.2"])
|
56
|
+
s.add_dependency(%q<haml>, [">= 3.0.24"])
|
54
57
|
end
|
55
58
|
end
|
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
|
+
- 20
|
9
|
+
version: 0.1.20
|
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: 2011-02-
|
17
|
+
date: 2011-02-25 00:00:00 +01:00
|
18
18
|
default_executable:
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
@@ -115,6 +115,20 @@ dependencies:
|
|
115
115
|
version: 0.4.2
|
116
116
|
type: :runtime
|
117
117
|
version_requirements: *id007
|
118
|
+
- !ruby/object:Gem::Dependency
|
119
|
+
name: haml
|
120
|
+
prerelease: false
|
121
|
+
requirement: &id008 !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - ">="
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
segments:
|
126
|
+
- 3
|
127
|
+
- 0
|
128
|
+
- 24
|
129
|
+
version: 3.0.24
|
130
|
+
type: :runtime
|
131
|
+
version_requirements: *id008
|
118
132
|
description: RDF web scraper
|
119
133
|
email: joseignacio.fernandez@gmail.com
|
120
134
|
executables:
|