cobweb 0.0.60 → 0.0.61

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 v0.0.60
2
+ h1. Cobweb v0.0.61
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
- "0.0.60"
6
+ "0.0.61"
7
7
  end
8
8
 
9
9
  end
@@ -35,8 +35,11 @@ class CrawlJob
35
35
  # if there is no limit or we're still under it lets get the url
36
36
  if within_crawl_limits?(content_request[:crawl_limit])
37
37
  begin
38
+ # move the url from the queued list to the crawled list - for both the original url, and the content url (to handle redirects)
38
39
  @redis.srem "queued", content_request[:url]
39
40
  @redis.sadd "crawled", content_request[:url]
41
+ @redis.srem "queued", content[:url]
42
+ @redis.sadd "crawled", content[:url]
40
43
  # increment the counter if we are not limiting by page only || we are limiting count by page and it is a page
41
44
  if content_request[:crawl_limit_by_page]
42
45
  if content[:mime_type].match("text/html")
@@ -207,7 +207,6 @@ def clear_queues
207
207
  Resque.queues.each do |queue|
208
208
  Resque.remove_queue(queue)
209
209
  end
210
- puts "Cleared"
211
210
 
212
211
  Resque.size("cobweb_process_job").should == 0
213
212
  Resque.size("cobweb_finished_job").should == 0
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: 0.0.60
4
+ version: 0.0.61
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: 2012-07-12 00:00:00.000000000 Z
12
+ date: 2012-07-17 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: resque
16
- requirement: &70111532832640 !ruby/object:Gem::Requirement
16
+ requirement: &70301996170680 !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: *70111532832640
24
+ version_requirements: *70301996170680
25
25
  - !ruby/object:Gem::Dependency
26
26
  name: redis
27
- requirement: &70111532832160 !ruby/object:Gem::Requirement
27
+ requirement: &70301996168960 !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: *70111532832160
35
+ version_requirements: *70301996168960
36
36
  - !ruby/object:Gem::Dependency
37
37
  name: nokogiri
38
- requirement: &70111532831300 !ruby/object:Gem::Requirement
38
+ requirement: &70301996168220 !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: *70111532831300
46
+ version_requirements: *70301996168220
47
47
  - !ruby/object:Gem::Dependency
48
48
  name: addressable
49
- requirement: &70111532830260 !ruby/object:Gem::Requirement
49
+ requirement: &70301996167040 !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: *70111532830260
57
+ version_requirements: *70301996167040
58
58
  - !ruby/object:Gem::Dependency
59
59
  name: rspec
60
- requirement: &70111532829180 !ruby/object:Gem::Requirement
60
+ requirement: &70301996165600 !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: *70111532829180
68
+ version_requirements: *70301996165600
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: awesome_print
71
- requirement: &70111532844220 !ruby/object:Gem::Requirement
71
+ requirement: &70301996180600 !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: *70111532844220
79
+ version_requirements: *70301996180600
80
80
  - !ruby/object:Gem::Dependency
81
81
  name: sinatra
82
- requirement: &70111532843480 !ruby/object:Gem::Requirement
82
+ requirement: &70301996179980 !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: *70111532843480
90
+ version_requirements: *70301996179980
91
91
  - !ruby/object:Gem::Dependency
92
92
  name: thin
93
- requirement: &70111532842880 !ruby/object:Gem::Requirement
93
+ requirement: &70301996179420 !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: *70111532842880
101
+ version_requirements: *70301996179420
102
102
  - !ruby/object:Gem::Dependency
103
103
  name: haml
104
- requirement: &70111532842240 !ruby/object:Gem::Requirement
104
+ requirement: &70301996178900 !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: *70111532842240
112
+ version_requirements: *70301996178900
113
113
  - !ruby/object:Gem::Dependency
114
114
  name: namespaced_redis
115
- requirement: &70111532841500 !ruby/object:Gem::Requirement
115
+ requirement: &70301996178200 !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: *70111532841500
123
+ version_requirements: *70301996178200
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