cobweb 0.0.42 → 0.0.43

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 v0.0.42
2
+ h1. Cobweb v0.0.43
3
3
 
4
4
  h2. Intro
5
5
 
@@ -20,7 +20,7 @@ class Cobweb
20
20
  # investigate using event machine for single threaded crawling
21
21
 
22
22
  def self.version
23
- "0.0.42"
23
+ "0.0.43"
24
24
  end
25
25
 
26
26
  def method_missing(method_sym, *arguments, &block)
@@ -42,7 +42,7 @@ class CobwebCrawler
42
42
  puts "http://localhost:4567/statistics/#{@crawl_id}"
43
43
  puts ""
44
44
 
45
- @redis.sadd "queued", base_url
45
+ @redis.sadd("queued", base_url) unless @redis.sismember("crawled", base_url) || @redis.sismember("queued", base_url)
46
46
  crawl_counter = @redis.scard("crawled").to_i
47
47
  queue_counter = @redis.scard("queued").to_i
48
48
 
@@ -52,8 +52,6 @@ class CobwebCrawler
52
52
  thread = Thread.new do
53
53
 
54
54
  url = @redis.spop "queued"
55
- crawl_counter = @redis.scard("crawled").to_i
56
- queue_counter = @redis.scard("queued").to_i
57
55
 
58
56
  @options[:url] = url
59
57
  unless @redis.sismember("crawled", url.to_s)
@@ -79,10 +77,10 @@ class CobwebCrawler
79
77
  puts "Added #{link.to_s} to queue" if @debug
80
78
  @redis.sadd "queued", link
81
79
  end
82
-
83
- crawl_counter = @redis.scard("crawled").to_i
84
- queue_counter = @redis.scard("queued").to_i
85
-
80
+
81
+ crawl_counter = crawl_counter + 1 #@redis.scard("crawled").to_i
82
+ queue_counter = queue_counter - 1 #@redis.scard("queued").to_i
83
+
86
84
  @stats.update_statistics(content)
87
85
  @stats.update_status("Completed #{url}.")
88
86
  puts "Crawled: #{crawl_counter.to_i} Limit: #{@options[:crawl_limit].to_i} Queued: #{queue_counter.to_i}" if @debug
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: 0.0.42
4
+ version: 0.0.43
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: 2012-05-02 00:00:00.000000000 Z
12
+ date: 2012-05-03 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: resque
16
- requirement: &70246513464500 !ruby/object:Gem::Requirement
16
+ requirement: &70139604510540 !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: *70246513464500
24
+ version_requirements: *70139604510540
25
25
  - !ruby/object:Gem::Dependency
26
26
  name: redis
27
- requirement: &70246513464080 !ruby/object:Gem::Requirement
27
+ requirement: &70139604510120 !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: *70246513464080
35
+ version_requirements: *70139604510120
36
36
  - !ruby/object:Gem::Dependency
37
37
  name: nokogiri
38
- requirement: &70246513463660 !ruby/object:Gem::Requirement
38
+ requirement: &70139604509700 !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: *70246513463660
46
+ version_requirements: *70139604509700
47
47
  - !ruby/object:Gem::Dependency
48
48
  name: addressable
49
- requirement: &70246513463240 !ruby/object:Gem::Requirement
49
+ requirement: &70139604509280 !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: *70246513463240
57
+ version_requirements: *70139604509280
58
58
  - !ruby/object:Gem::Dependency
59
59
  name: rspec
60
- requirement: &70246513462820 !ruby/object:Gem::Requirement
60
+ requirement: &70139604508860 !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: *70246513462820
68
+ version_requirements: *70139604508860
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: awesome_print
71
- requirement: &70246513462400 !ruby/object:Gem::Requirement
71
+ requirement: &70139604508440 !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: *70246513462400
79
+ version_requirements: *70139604508440
80
80
  - !ruby/object:Gem::Dependency
81
81
  name: sinatra
82
- requirement: &70246513461980 !ruby/object:Gem::Requirement
82
+ requirement: &70139604508020 !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: *70246513461980
90
+ version_requirements: *70139604508020
91
91
  - !ruby/object:Gem::Dependency
92
92
  name: thin
93
- requirement: &70246513461560 !ruby/object:Gem::Requirement
93
+ requirement: &70139604523960 !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: *70246513461560
101
+ version_requirements: *70139604523960
102
102
  - !ruby/object:Gem::Dependency
103
103
  name: haml
104
- requirement: &70246513461140 !ruby/object:Gem::Requirement
104
+ requirement: &70139604523540 !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: *70246513461140
112
+ version_requirements: *70139604523540
113
113
  - !ruby/object:Gem::Dependency
114
114
  name: namespaced_redis
115
- requirement: &70246513460720 !ruby/object:Gem::Requirement
115
+ requirement: &70139604523120 !ruby/object:Gem::Requirement
116
116
  none: false
117
117
  requirements:
118
118
  - - ! '>='
@@ -120,7 +120,7 @@ dependencies:
120
120
  version: '0'
121
121
  type: :runtime
122
122
  prerelease: false
123
- version_requirements: *70246513460720
123
+ version_requirements: *70139604523120
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