crawl 1.0.2 → 1.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/crawl.gemspec +2 -2
- data/lib/crawl/engine.rb +1 -1
- data/lib/crawl/version.rb +1 -1
- metadata +19 -29
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4825e68f15b25c5f26947ea149b6c835ced7bdf8
|
4
|
+
data.tar.gz: fdebd71a13a40f51cb20a635c5e02ea6dd9a4f6f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 25a485be0c41e3f23b60f5974806757c6a6ab6888bbadbf0df317b3c7bce1825616026a5d1cd0c2feaf223a7af844b3630de0d6e547108d87d77c00b89dd27c0
|
7
|
+
data.tar.gz: abe1b5261102f0cd498d75caedef412e4bee3a7995401fe3c88ef0619b01c4d18a46904db4d5b778916fbf76f1ae7faf0935758463ab45e389ef98915ff633e7
|
data/crawl.gemspec
CHANGED
@@ -16,6 +16,6 @@ Gem::Specification.new do |gem|
|
|
16
16
|
gem.version = Crawl::VERSION
|
17
17
|
gem.add_dependency('nokogiri')
|
18
18
|
gem.add_dependency('rest-client')
|
19
|
-
gem.add_dependency('eventmachine', '
|
20
|
-
gem.add_dependency('em-http-request')
|
19
|
+
gem.add_dependency('eventmachine', '1.0.1')
|
20
|
+
gem.add_dependency('em-http-request', '1.0.3')
|
21
21
|
end
|
data/lib/crawl/engine.rb
CHANGED
@@ -105,7 +105,7 @@ private
|
|
105
105
|
raw_links = anchors.map{|anchor| anchor['href']}
|
106
106
|
raw_links.compact!
|
107
107
|
raw_links.map!{|link| link.sub(options[:domain], '')}
|
108
|
-
raw_links.delete_if{|link| link =~ %r{^http(s)?://}}
|
108
|
+
raw_links.delete_if{|link| link =~ %r{^http(s)?://} && !link.include?(options[:domain])}
|
109
109
|
raw_links.delete_if{|link| IGNORE.any?{|pattern| link =~ pattern}}
|
110
110
|
raw_links.map{ |url| Page.new(@register, url, page.url) }
|
111
111
|
end
|
data/lib/crawl/version.rb
CHANGED
metadata
CHANGED
@@ -1,80 +1,71 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
5
|
-
prerelease:
|
4
|
+
version: 1.0.3
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Tor Erik Linnerud
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date: 2013-
|
11
|
+
date: 2013-03-15 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: nokogiri
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
|
-
- -
|
17
|
+
- - '>='
|
20
18
|
- !ruby/object:Gem::Version
|
21
19
|
version: '0'
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
|
-
- -
|
24
|
+
- - '>='
|
28
25
|
- !ruby/object:Gem::Version
|
29
26
|
version: '0'
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: rest-client
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
|
-
- -
|
31
|
+
- - '>='
|
36
32
|
- !ruby/object:Gem::Version
|
37
33
|
version: '0'
|
38
34
|
type: :runtime
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
|
-
- -
|
38
|
+
- - '>='
|
44
39
|
- !ruby/object:Gem::Version
|
45
40
|
version: '0'
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: eventmachine
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
|
-
- -
|
45
|
+
- - '='
|
52
46
|
- !ruby/object:Gem::Version
|
53
|
-
version: 1.0.
|
47
|
+
version: 1.0.1
|
54
48
|
type: :runtime
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
|
-
- -
|
52
|
+
- - '='
|
60
53
|
- !ruby/object:Gem::Version
|
61
|
-
version: 1.0.
|
54
|
+
version: 1.0.1
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
56
|
name: em-http-request
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
|
-
- -
|
59
|
+
- - '='
|
68
60
|
- !ruby/object:Gem::Version
|
69
|
-
version:
|
61
|
+
version: 1.0.3
|
70
62
|
type: :runtime
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
|
-
- -
|
66
|
+
- - '='
|
76
67
|
- !ruby/object:Gem::Version
|
77
|
-
version:
|
68
|
+
version: 1.0.3
|
78
69
|
description: Crawl all pages on a domain, checking for errors
|
79
70
|
email:
|
80
71
|
- tor@alphasights.com
|
@@ -98,27 +89,26 @@ files:
|
|
98
89
|
- lib/crawl/version.rb
|
99
90
|
homepage: http://github.com/alphasights/crawl
|
100
91
|
licenses: []
|
92
|
+
metadata: {}
|
101
93
|
post_install_message:
|
102
94
|
rdoc_options: []
|
103
95
|
require_paths:
|
104
96
|
- lib
|
105
97
|
required_ruby_version: !ruby/object:Gem::Requirement
|
106
|
-
none: false
|
107
98
|
requirements:
|
108
|
-
- -
|
99
|
+
- - '>='
|
109
100
|
- !ruby/object:Gem::Version
|
110
101
|
version: '0'
|
111
102
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
112
|
-
none: false
|
113
103
|
requirements:
|
114
|
-
- -
|
104
|
+
- - '>='
|
115
105
|
- !ruby/object:Gem::Version
|
116
106
|
version: '0'
|
117
107
|
requirements: []
|
118
108
|
rubyforge_project:
|
119
|
-
rubygems_version:
|
109
|
+
rubygems_version: 2.0.0
|
120
110
|
signing_key:
|
121
|
-
specification_version:
|
111
|
+
specification_version: 4
|
122
112
|
summary: Crawl pages witin a domain, reporting any page that returns a bad response
|
123
113
|
code
|
124
114
|
test_files: []
|