cobweb 0.0.52 → 0.0.53
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/README.textile +1 -1
- data/lib/cobweb_version.rb +1 -1
- data/lib/content_link_parser.rb +1 -0
- data/spec/cobweb/content_link_parser_spec.rb +10 -3
- data/spec/samples/sample_html_links.html +5 -0
- metadata +21 -21
data/README.textile
CHANGED
data/lib/cobweb_version.rb
CHANGED
data/lib/content_link_parser.rb
CHANGED
@@ -42,6 +42,7 @@ class ContentLinkParser
|
|
42
42
|
data = link_data
|
43
43
|
links = data.keys.map{|key| data[key]}.flatten.uniq
|
44
44
|
links = links.map{|link| UriHelper.join_no_fragment(@url, link).to_s }
|
45
|
+
links = links.reject{|link| link =~ /([^\/]+?)\/([^\/]+?)\/.*?\1\/\2/ }
|
45
46
|
links = links.select{|link| options[:valid_schemes].include? link.split(':')[0].to_sym}
|
46
47
|
links
|
47
48
|
end
|
@@ -29,7 +29,7 @@ describe ContentLinkParser do
|
|
29
29
|
end
|
30
30
|
it "should return the correct links" do
|
31
31
|
links = @content_parser.links
|
32
|
-
links.length.should ==
|
32
|
+
links.length.should == 11
|
33
33
|
end
|
34
34
|
end
|
35
35
|
describe "returning image links" do
|
@@ -92,12 +92,12 @@ describe ContentLinkParser do
|
|
92
92
|
link_data.should be_an_instance_of Hash
|
93
93
|
|
94
94
|
link_data.keys.length.should == 5
|
95
|
-
link_data[:links].length.should ==
|
95
|
+
link_data[:links].length.should == 11
|
96
96
|
end
|
97
97
|
|
98
98
|
it "should return all http and https links by default" do
|
99
99
|
links = @content_parser.all_links
|
100
|
-
links.count.should ==
|
100
|
+
links.count.should == 13
|
101
101
|
end
|
102
102
|
|
103
103
|
it "should return all http and https links by default" do
|
@@ -110,6 +110,13 @@ describe ContentLinkParser do
|
|
110
110
|
links = @content_parser.all_links(:valid_schemes => [:https])
|
111
111
|
links.count.should == 1
|
112
112
|
end
|
113
|
+
|
114
|
+
it "should detect and not return link loops" do
|
115
|
+
links = @content_parser.all_links
|
116
|
+
links.should include("http://www.ge.com/repeated1/repeated2/nothing/repeated1/")
|
117
|
+
links.should_not include("http://www.ge.com/repeated1/repeated2/nothing/repeated1/repeated2")
|
118
|
+
links.should include("http://www.ge.com/repeated1/repeated2/nothing/repeated1/asdf/repeated2")
|
119
|
+
end
|
113
120
|
end
|
114
121
|
|
115
122
|
describe "ignoring default tags" do
|
@@ -27,6 +27,11 @@
|
|
27
27
|
<a href="mailto:stewart@theizone.co.uk">Click Here to email </a>
|
28
28
|
<a href="javascript:alert('javascript clicked');">click here for javscript</a>
|
29
29
|
<a href="https://sampleurl-a.com/">Click Here for SSL link to URL 1</a>
|
30
|
+
<a href="http://www.ge.com/repeated1/repeated2/nothing/repeated1/"></a>
|
31
|
+
<a href="http://www.ge.com/repeated1/repeated2/nothing/repeated1/repeated2"></a>
|
32
|
+
<a href="http://www.ge.com/repeated1/repeated2/nothing/repeated1/asdf/repeated2"></a>
|
33
|
+
|
34
|
+
<a href="http://www.ge.com/citizenship/our-priorities/our-products-services/news/citizenship-in-the-news/about-citizenship/our-impact/about-citizenship/performance-against-commitments/metrics/environment-health-safety/about-citizenship/our-impact/metrics/suppliers/about-citizenship/leadership-messages/about-citizenship/awards-recognition/our-commitment-areas/our-people/our-commitment-areas/our-customers/metrics/suppliers/about-citizenship/leadership-messages/our-commitment-areas/our-suppliers/metrics/ecomagination-data/about-citizenship/awards-recognition/news/videos/news/news/videos/about-citizenship/awards-recognition/">looped link</a>
|
30
35
|
<frameset><frame src="http://sampleurl-frame.com/"></frame></frameset>
|
31
36
|
|
32
37
|
<map id="testmap"><area href="http://sampleurl-area"></area>></map>
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: cobweb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.53
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2012-05-08 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70165685677520 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70165685677520
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70165685676500 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: '0'
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *70165685676500
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70165685675420 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *70165685675420
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70165685673680 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *70165685673680
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70165685671300 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ! '>='
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: '0'
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *70165685671300
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70165685694460 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ! '>='
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: '0'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *70165685694460
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70165685692120 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ! '>='
|
@@ -87,10 +87,10 @@ dependencies:
|
|
87
87
|
version: '0'
|
88
88
|
type: :runtime
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *70165685692120
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70165685703520 !ruby/object:Gem::Requirement
|
94
94
|
none: false
|
95
95
|
requirements:
|
96
96
|
- - ! '>='
|
@@ -98,10 +98,10 @@ dependencies:
|
|
98
98
|
version: '0'
|
99
99
|
type: :runtime
|
100
100
|
prerelease: false
|
101
|
-
version_requirements: *
|
101
|
+
version_requirements: *70165685703520
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70165685702520 !ruby/object:Gem::Requirement
|
105
105
|
none: false
|
106
106
|
requirements:
|
107
107
|
- - ! '>='
|
@@ -109,10 +109,10 @@ dependencies:
|
|
109
109
|
version: '0'
|
110
110
|
type: :runtime
|
111
111
|
prerelease: false
|
112
|
-
version_requirements: *
|
112
|
+
version_requirements: *70165685702520
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70165685701400 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,7 +120,7 @@ dependencies:
|
|
120
120
|
version: 1.0.2
|
121
121
|
type: :runtime
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70165685701400
|
124
124
|
description: Web Crawler that uses resque background job engine to allow you to cluster
|
125
125
|
your crawl.
|
126
126
|
email: stewart@rockwellcottage.com
|