webrobots 0.0.9 → 0.0.10
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +1 -1
- data/Gemfile.lock +5 -5
- data/Rakefile +4 -3
- data/VERSION +1 -1
- data/lib/webrobots/robotstxt.rb +1 -1
- data/lib/webrobots/robotstxt.ry +1 -1
- data/test/test_webrobots.rb +37 -0
- data/webrobots.gemspec +9 -13
- metadata +70 -111
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
@@ -2,13 +2,13 @@ GEM
|
|
2
2
|
remote: http://rubygems.org/
|
3
3
|
specs:
|
4
4
|
git (1.2.5)
|
5
|
-
jeweler (1.
|
6
|
-
bundler (~> 1.0
|
5
|
+
jeweler (1.6.2)
|
6
|
+
bundler (~> 1.0)
|
7
7
|
git (>= 1.2.5)
|
8
8
|
rake
|
9
|
-
nokogiri (1.4.
|
9
|
+
nokogiri (1.4.6)
|
10
10
|
racc (1.4.6)
|
11
|
-
rake (0.
|
11
|
+
rake (0.9.2)
|
12
12
|
rcov (0.9.9)
|
13
13
|
shoulda (2.11.3)
|
14
14
|
|
@@ -17,7 +17,7 @@ PLATFORMS
|
|
17
17
|
|
18
18
|
DEPENDENCIES
|
19
19
|
bundler (~> 1.0.0)
|
20
|
-
jeweler (~> 1.
|
20
|
+
jeweler (~> 1.6.2)
|
21
21
|
nokogiri (>= 1.4.4)
|
22
22
|
racc
|
23
23
|
rcov
|
data/Rakefile
CHANGED
@@ -1,3 +1,5 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
1
3
|
require 'rubygems'
|
2
4
|
require 'bundler'
|
3
5
|
begin
|
@@ -21,9 +23,7 @@ This library helps write robots.txt compliant web robots in Ruby.
|
|
21
23
|
EOS
|
22
24
|
gem.email = "knu@idaemons.org"
|
23
25
|
gem.authors = ["Akinori MUSHA"]
|
24
|
-
#
|
25
|
-
# and development dependencies are only needed for development (ie running rake tasks, tests, etc)
|
26
|
-
# gem.add_runtime_dependency 'jabber4r', '> 0.1'
|
26
|
+
# dependencies defined in Gemfile
|
27
27
|
end
|
28
28
|
Jeweler::RubygemsDotOrgTasks.new
|
29
29
|
|
@@ -39,6 +39,7 @@ Rcov::RcovTask.new do |test|
|
|
39
39
|
test.libs << 'test'
|
40
40
|
test.pattern = 'test/**/test_*.rb'
|
41
41
|
test.verbose = true
|
42
|
+
test.rcov_opts << '--exclude "gems/*"'
|
42
43
|
end
|
43
44
|
|
44
45
|
task :default => :test
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0.
|
1
|
+
0.0.10
|
data/lib/webrobots/robotstxt.rb
CHANGED
data/lib/webrobots/robotstxt.ry
CHANGED
data/test/test_webrobots.rb
CHANGED
@@ -545,4 +545,41 @@ Disallow: /
|
|
545
545
|
assert_equal 'content', body
|
546
546
|
end
|
547
547
|
end
|
548
|
+
|
549
|
+
context "robots.txt with a space at the end of the last line" do
|
550
|
+
setup do
|
551
|
+
@robots = WebRobots.new('RandomBot', :http_get => lambda { |uri|
|
552
|
+
res = case uri.to_s
|
553
|
+
when 'http://site1.example.com/robots.txt'
|
554
|
+
<<-'TXT'
|
555
|
+
User-agent: *
|
556
|
+
Request-rate: 1/30
|
557
|
+
Disallow: /util/
|
558
|
+
|
559
|
+
Sitemap: http://site1.example.com/text/sitemap.xml
|
560
|
+
|
561
|
+
TXT
|
562
|
+
when 'http://site2.example.com/robots.txt'
|
563
|
+
<<-'TXT'
|
564
|
+
User-agent: *
|
565
|
+
Request-rate: 1/30
|
566
|
+
Disallow: /util/
|
567
|
+
|
568
|
+
Sitemap: http://site2.example.com/text/sitemap.xml
|
569
|
+
TXT
|
570
|
+
else
|
571
|
+
raise "#{uri} is not supposed to be fetched"
|
572
|
+
end
|
573
|
+
# This chomp is actually key to the test. Remove the final EOL.
|
574
|
+
# The final line should be the one ending with the space.
|
575
|
+
res.chomp
|
576
|
+
})
|
577
|
+
end
|
578
|
+
|
579
|
+
should "be properly parsed" do
|
580
|
+
assert_equal(["http://site1.example.com/text/sitemap.xml"], @robots.sitemaps("http://site1.example.com/"))
|
581
|
+
assert_equal(["http://site2.example.com/text/sitemap.xml"], @robots.sitemaps("http://site2.example.com/"))
|
582
|
+
end
|
583
|
+
end
|
584
|
+
|
548
585
|
end
|
data/webrobots.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{webrobots}
|
8
|
-
s.version = "0.0.
|
8
|
+
s.version = "0.0.10"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
-
s.authors = [
|
12
|
-
s.date = %q{2011-
|
11
|
+
s.authors = [%q{Akinori MUSHA}]
|
12
|
+
s.date = %q{2011-07-01}
|
13
13
|
s.description = %q{This library helps write robots.txt compliant web robots in Ruby.
|
14
14
|
}
|
15
15
|
s.email = %q{knu@idaemons.org}
|
@@ -33,14 +33,10 @@ Gem::Specification.new do |s|
|
|
33
33
|
"test/test_webrobots.rb",
|
34
34
|
"webrobots.gemspec"
|
35
35
|
]
|
36
|
-
s.licenses = [
|
37
|
-
s.require_paths = [
|
38
|
-
s.rubygems_version = %q{1.
|
36
|
+
s.licenses = [%q{2-clause BSDL}]
|
37
|
+
s.require_paths = [%q{lib}]
|
38
|
+
s.rubygems_version = %q{1.8.5}
|
39
39
|
s.summary = %q{A Ruby library to help write robots.txt compliant web robots}
|
40
|
-
s.test_files = [
|
41
|
-
"test/helper.rb",
|
42
|
-
"test/test_webrobots.rb"
|
43
|
-
]
|
44
40
|
|
45
41
|
if s.respond_to? :specification_version then
|
46
42
|
s.specification_version = 3
|
@@ -50,14 +46,14 @@ Gem::Specification.new do |s|
|
|
50
46
|
s.add_development_dependency(%q<racc>, [">= 0"])
|
51
47
|
s.add_development_dependency(%q<shoulda>, [">= 0"])
|
52
48
|
s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
|
53
|
-
s.add_development_dependency(%q<jeweler>, ["~> 1.
|
49
|
+
s.add_development_dependency(%q<jeweler>, ["~> 1.6.2"])
|
54
50
|
s.add_development_dependency(%q<rcov>, [">= 0"])
|
55
51
|
else
|
56
52
|
s.add_dependency(%q<nokogiri>, [">= 1.4.4"])
|
57
53
|
s.add_dependency(%q<racc>, [">= 0"])
|
58
54
|
s.add_dependency(%q<shoulda>, [">= 0"])
|
59
55
|
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
60
|
-
s.add_dependency(%q<jeweler>, ["~> 1.
|
56
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.2"])
|
61
57
|
s.add_dependency(%q<rcov>, [">= 0"])
|
62
58
|
end
|
63
59
|
else
|
@@ -65,7 +61,7 @@ Gem::Specification.new do |s|
|
|
65
61
|
s.add_dependency(%q<racc>, [">= 0"])
|
66
62
|
s.add_dependency(%q<shoulda>, [">= 0"])
|
67
63
|
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
68
|
-
s.add_dependency(%q<jeweler>, ["~> 1.
|
64
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.2"])
|
69
65
|
s.add_dependency(%q<rcov>, [">= 0"])
|
70
66
|
end
|
71
67
|
end
|
metadata
CHANGED
@@ -1,125 +1,92 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: webrobots
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.10
|
5
5
|
prerelease:
|
6
|
-
segments:
|
7
|
-
- 0
|
8
|
-
- 0
|
9
|
-
- 9
|
10
|
-
version: 0.0.9
|
11
6
|
platform: ruby
|
12
|
-
authors:
|
7
|
+
authors:
|
13
8
|
- Akinori MUSHA
|
14
9
|
autorequire:
|
15
10
|
bindir: bin
|
16
11
|
cert_chain: []
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
dependencies:
|
21
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2011-07-01 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
22
15
|
name: nokogiri
|
23
|
-
|
16
|
+
requirement: &17196464340 !ruby/object:Gem::Requirement
|
24
17
|
none: false
|
25
|
-
requirements:
|
26
|
-
- -
|
27
|
-
- !ruby/object:Gem::Version
|
28
|
-
hash: 15
|
29
|
-
segments:
|
30
|
-
- 1
|
31
|
-
- 4
|
32
|
-
- 4
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
33
21
|
version: 1.4.4
|
34
|
-
prerelease: false
|
35
22
|
type: :runtime
|
36
|
-
|
37
|
-
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *17196464340
|
25
|
+
- !ruby/object:Gem::Dependency
|
38
26
|
name: racc
|
39
|
-
|
27
|
+
requirement: &17196463180 !ruby/object:Gem::Requirement
|
40
28
|
none: false
|
41
|
-
requirements:
|
42
|
-
- -
|
43
|
-
- !ruby/object:Gem::Version
|
44
|
-
|
45
|
-
segments:
|
46
|
-
- 0
|
47
|
-
version: "0"
|
48
|
-
prerelease: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
49
33
|
type: :development
|
50
|
-
|
51
|
-
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *17196463180
|
36
|
+
- !ruby/object:Gem::Dependency
|
52
37
|
name: shoulda
|
53
|
-
|
38
|
+
requirement: &17196462340 !ruby/object:Gem::Requirement
|
54
39
|
none: false
|
55
|
-
requirements:
|
56
|
-
- -
|
57
|
-
- !ruby/object:Gem::Version
|
58
|
-
|
59
|
-
segments:
|
60
|
-
- 0
|
61
|
-
version: "0"
|
62
|
-
prerelease: false
|
40
|
+
requirements:
|
41
|
+
- - ! '>='
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
63
44
|
type: :development
|
64
|
-
|
65
|
-
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: *17196462340
|
47
|
+
- !ruby/object:Gem::Dependency
|
66
48
|
name: bundler
|
67
|
-
|
49
|
+
requirement: &17196461320 !ruby/object:Gem::Requirement
|
68
50
|
none: false
|
69
|
-
requirements:
|
51
|
+
requirements:
|
70
52
|
- - ~>
|
71
|
-
- !ruby/object:Gem::Version
|
72
|
-
hash: 23
|
73
|
-
segments:
|
74
|
-
- 1
|
75
|
-
- 0
|
76
|
-
- 0
|
53
|
+
- !ruby/object:Gem::Version
|
77
54
|
version: 1.0.0
|
78
|
-
prerelease: false
|
79
55
|
type: :development
|
80
|
-
|
81
|
-
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *17196461320
|
58
|
+
- !ruby/object:Gem::Dependency
|
82
59
|
name: jeweler
|
83
|
-
|
60
|
+
requirement: &17196460320 !ruby/object:Gem::Requirement
|
84
61
|
none: false
|
85
|
-
requirements:
|
62
|
+
requirements:
|
86
63
|
- - ~>
|
87
|
-
- !ruby/object:Gem::Version
|
88
|
-
|
89
|
-
segments:
|
90
|
-
- 1
|
91
|
-
- 5
|
92
|
-
- 1
|
93
|
-
version: 1.5.1
|
94
|
-
prerelease: false
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: 1.6.2
|
95
66
|
type: :development
|
96
|
-
|
97
|
-
|
67
|
+
prerelease: false
|
68
|
+
version_requirements: *17196460320
|
69
|
+
- !ruby/object:Gem::Dependency
|
98
70
|
name: rcov
|
99
|
-
|
71
|
+
requirement: &17196459400 !ruby/object:Gem::Requirement
|
100
72
|
none: false
|
101
|
-
requirements:
|
102
|
-
- -
|
103
|
-
- !ruby/object:Gem::Version
|
104
|
-
|
105
|
-
segments:
|
106
|
-
- 0
|
107
|
-
version: "0"
|
108
|
-
prerelease: false
|
73
|
+
requirements:
|
74
|
+
- - ! '>='
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
109
77
|
type: :development
|
110
|
-
|
111
|
-
|
112
|
-
|
78
|
+
prerelease: false
|
79
|
+
version_requirements: *17196459400
|
80
|
+
description: ! 'This library helps write robots.txt compliant web robots in Ruby.
|
113
81
|
|
82
|
+
'
|
114
83
|
email: knu@idaemons.org
|
115
84
|
executables: []
|
116
|
-
|
117
85
|
extensions: []
|
118
|
-
|
119
|
-
extra_rdoc_files:
|
86
|
+
extra_rdoc_files:
|
120
87
|
- LICENSE.txt
|
121
88
|
- README.rdoc
|
122
|
-
files:
|
89
|
+
files:
|
123
90
|
- .document
|
124
91
|
- Gemfile
|
125
92
|
- Gemfile.lock
|
@@ -134,40 +101,32 @@ files:
|
|
134
101
|
- test/helper.rb
|
135
102
|
- test/test_webrobots.rb
|
136
103
|
- webrobots.gemspec
|
137
|
-
has_rdoc: true
|
138
104
|
homepage:
|
139
|
-
licenses:
|
105
|
+
licenses:
|
140
106
|
- 2-clause BSDL
|
141
107
|
post_install_message:
|
142
108
|
rdoc_options: []
|
143
|
-
|
144
|
-
require_paths:
|
109
|
+
require_paths:
|
145
110
|
- lib
|
146
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
111
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
147
112
|
none: false
|
148
|
-
requirements:
|
149
|
-
- -
|
150
|
-
- !ruby/object:Gem::Version
|
151
|
-
|
152
|
-
segments:
|
113
|
+
requirements:
|
114
|
+
- - ! '>='
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '0'
|
117
|
+
segments:
|
153
118
|
- 0
|
154
|
-
|
155
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
119
|
+
hash: 1141598142888730213
|
120
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
156
121
|
none: false
|
157
|
-
requirements:
|
158
|
-
- -
|
159
|
-
- !ruby/object:Gem::Version
|
160
|
-
|
161
|
-
segments:
|
162
|
-
- 0
|
163
|
-
version: "0"
|
122
|
+
requirements:
|
123
|
+
- - ! '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
164
126
|
requirements: []
|
165
|
-
|
166
127
|
rubyforge_project:
|
167
|
-
rubygems_version: 1.
|
128
|
+
rubygems_version: 1.8.5
|
168
129
|
signing_key:
|
169
130
|
specification_version: 3
|
170
131
|
summary: A Ruby library to help write robots.txt compliant web robots
|
171
|
-
test_files:
|
172
|
-
- test/helper.rb
|
173
|
-
- test/test_webrobots.rb
|
132
|
+
test_files: []
|