cobweb 0.0.64 → 0.0.65

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.
@@ -1,5 +1,5 @@
1
1
 
2
- h1. Cobweb v0.0.64
2
+ h1. Cobweb v0.0.65
3
3
  !https://secure.travis-ci.org/stewartmckee/cobweb.png?branch=master!
4
4
 
5
5
  h2. Intro
@@ -3,7 +3,7 @@ class CobwebVersion
3
3
 
4
4
  # Returns a string of the current version
5
5
  def self.version
6
- "0.0.64"
6
+ "0.0.65"
7
7
  end
8
8
 
9
9
  end
@@ -25,7 +25,7 @@ class CrawlJob
25
25
  @debug = content_request[:debug]
26
26
 
27
27
  decrement_queue_counter
28
-
28
+
29
29
  # check we haven't crawled this url before
30
30
  unless @redis.sismember "crawled", content_request[:url]
31
31
  # if there is no limit or we're still under it lets get the url
@@ -60,7 +60,8 @@ class CrawlJob
60
60
  @cobweb_links = CobwebLinks.new(content_request)
61
61
  if within_queue_limits?(content_request[:crawl_limit])
62
62
  internal_links = ContentLinkParser.new(content_request[:url], content[:body], content_request).all_links(:valid_schemes => [:http, :https])
63
-
63
+ #get rid of duplicate links in the same page.
64
+ internal_links.uniq!
64
65
  # select the link if its internal
65
66
  internal_links.select! { |link| @cobweb_links.internal?(link) }
66
67
 
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: 0.0.64
4
+ version: 0.0.65
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors:
@@ -9,11 +9,11 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2012-08-20 00:00:00.000000000 Z
12
+ date: 2012-08-26 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: resque
16
- requirement: &70160920762100 !ruby/object:Gem::Requirement
16
+ requirement: &70202662972080 !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: *70160920762100
24
+ version_requirements: *70202662972080
25
25
  - !ruby/object:Gem::Dependency
26
26
  name: redis
27
- requirement: &70160920761600 !ruby/object:Gem::Requirement
27
+ requirement: &70202662971540 !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: *70160920761600
35
+ version_requirements: *70202662971540
36
36
  - !ruby/object:Gem::Dependency
37
37
  name: nokogiri
38
- requirement: &70160920760740 !ruby/object:Gem::Requirement
38
+ requirement: &70202662970680 !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: *70160920760740
46
+ version_requirements: *70202662970680
47
47
  - !ruby/object:Gem::Dependency
48
48
  name: addressable
49
- requirement: &70160920759800 !ruby/object:Gem::Requirement
49
+ requirement: &70202662969640 !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: *70160920759800
57
+ version_requirements: *70202662969640
58
58
  - !ruby/object:Gem::Dependency
59
59
  name: rspec
60
- requirement: &70160920758660 !ruby/object:Gem::Requirement
60
+ requirement: &70202662968800 !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: *70160920758660
68
+ version_requirements: *70202662968800
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: awesome_print
71
- requirement: &70160920773700 !ruby/object:Gem::Requirement
71
+ requirement: &70202662967880 !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: *70160920773700
79
+ version_requirements: *70202662967880
80
80
  - !ruby/object:Gem::Dependency
81
81
  name: sinatra
82
- requirement: &70160920772960 !ruby/object:Gem::Requirement
82
+ requirement: &70202662966760 !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: *70160920772960
90
+ version_requirements: *70202662966760
91
91
  - !ruby/object:Gem::Dependency
92
92
  name: thin
93
- requirement: &70160920772440 !ruby/object:Gem::Requirement
93
+ requirement: &70202662961760 !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: *70160920772440
101
+ version_requirements: *70202662961760
102
102
  - !ruby/object:Gem::Dependency
103
103
  name: haml
104
- requirement: &70160920771760 !ruby/object:Gem::Requirement
104
+ requirement: &70202662960800 !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: *70160920771760
112
+ version_requirements: *70202662960800
113
113
  - !ruby/object:Gem::Dependency
114
114
  name: namespaced_redis
115
- requirement: &70160920771040 !ruby/object:Gem::Requirement
115
+ requirement: &70202662958560 !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: *70160920771040
123
+ version_requirements: *70202662958560
124
124
  description: Cobweb is a web crawler that can use resque to cluster crawls to quickly
125
125
  crawl extremely large sites which is much more perofmant than multi-threaded crawlers. It
126
126
  is also a standalone crawler that has a sophisticated statistics monitoring interface