cobweb 0.0.75 → 0.0.76
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/crawl.rb +2 -1
- data/spec/cobweb/cobweb_crawl_spec.rb +36 -0
- data/spec/cobweb/cobweb_job_spec.rb +4 -4
- metadata +25 -24
data/README.textile
CHANGED
data/lib/cobweb_version.rb
CHANGED
data/lib/crawl.rb
CHANGED
@@ -5,7 +5,8 @@ module CobwebModule
|
|
5
5
|
@options = HashUtil.deep_symbolize_keys(options)
|
6
6
|
|
7
7
|
setup_defaults
|
8
|
-
|
8
|
+
|
9
|
+
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@options[:crawl_id]}", :redis => Redis.new(@options[:redis_options]))
|
9
10
|
@stats = Stats.new(@options)
|
10
11
|
@debug = @options[:debug]
|
11
12
|
@first_to_finish = false
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
|
+
|
3
|
+
describe CobwebModule::Crawl, :local_only => true do
|
4
|
+
|
5
|
+
before(:each) do
|
6
|
+
@local_redis = {:host => "127.0.0.1", :port => 6379}
|
7
|
+
@remote_redis = {:host => "192.168.100.16", :port => 6379}
|
8
|
+
|
9
|
+
@request = {:crawl_id => "test_crawl_id"}
|
10
|
+
end
|
11
|
+
|
12
|
+
describe "remote redis" do
|
13
|
+
before(:each) do
|
14
|
+
@local = CobwebModule::Crawl.new(:redis_options => @local_redis)
|
15
|
+
@remote = CobwebModule::Crawl.new(:redis_options => @remote_redis)
|
16
|
+
|
17
|
+
@local.redis.del("test_redis")
|
18
|
+
@remote.redis.del("test_redis")
|
19
|
+
|
20
|
+
end
|
21
|
+
it "should connect to the local redis" do
|
22
|
+
@local.redis.exists("test_redis").should be_false
|
23
|
+
@local.redis.set("test_redis", 1)
|
24
|
+
@local.redis.exists("test_redis").should be_true
|
25
|
+
|
26
|
+
@remote.redis.exists("test_redis").should be_false
|
27
|
+
end
|
28
|
+
it "should connect to the remote redis" do
|
29
|
+
@remote.redis.exists("test_redis").should be_false
|
30
|
+
@remote.redis.set("test_redis", 1)
|
31
|
+
@remote.redis.exists("test_redis").should be_true
|
32
|
+
|
33
|
+
@local.redis.exists("test_redis").should be_false
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -30,7 +30,7 @@ describe Cobweb, :local_only => true do
|
|
30
30
|
:debug => false,
|
31
31
|
:cache => nil
|
32
32
|
}
|
33
|
-
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", Redis.new)
|
33
|
+
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", :redis => Redis.new)
|
34
34
|
@cobweb = Cobweb.new @request
|
35
35
|
end
|
36
36
|
it "should not crawl anything if nothing has started" do
|
@@ -63,7 +63,7 @@ describe Cobweb, :local_only => true do
|
|
63
63
|
:debug => false,
|
64
64
|
:cache => nil
|
65
65
|
}
|
66
|
-
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", Redis.new)
|
66
|
+
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", :redis => Redis.new)
|
67
67
|
|
68
68
|
@cobweb = Cobweb.new @request
|
69
69
|
end
|
@@ -93,7 +93,7 @@ describe Cobweb, :local_only => true do
|
|
93
93
|
:cache => nil,
|
94
94
|
:valid_mime_types => ["text/html"]
|
95
95
|
}
|
96
|
-
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", Redis.new)
|
96
|
+
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", :redis => Redis.new)
|
97
97
|
@cobweb = Cobweb.new @request
|
98
98
|
end
|
99
99
|
|
@@ -118,7 +118,7 @@ describe Cobweb, :local_only => true do
|
|
118
118
|
:debug => false,
|
119
119
|
:cache => nil
|
120
120
|
}
|
121
|
-
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", Redis.new)
|
121
|
+
@redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{@request[:crawl_id]}", :redis => Redis.new)
|
122
122
|
end
|
123
123
|
|
124
124
|
# describe "crawling http://yepadeperrors.wordpress.com/ with limit of 20" do
|
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: 0.0.76
|
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: 2012-10-
|
12
|
+
date: 2012-10-18 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70301036171860 !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: *70301036171860
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70301036170940 !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: *70301036170940
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70301036169780 !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: *70301036169780
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70301036169040 !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: *70301036169040
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70301036167760 !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: *70301036167760
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70301036166240 !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: *70301036166240
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70301036164760 !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: *70301036164760
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70301036163660 !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: *70301036163660
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70301036162760 !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: *70301036162760
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70301036161620 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,10 +120,10 @@ dependencies:
|
|
120
120
|
version: 1.0.2
|
121
121
|
type: :runtime
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70301036161620
|
124
124
|
- !ruby/object:Gem::Dependency
|
125
125
|
name: json
|
126
|
-
requirement: &
|
126
|
+
requirement: &70301036161100 !ruby/object:Gem::Requirement
|
127
127
|
none: false
|
128
128
|
requirements:
|
129
129
|
- - ! '>='
|
@@ -131,7 +131,7 @@ dependencies:
|
|
131
131
|
version: '0'
|
132
132
|
type: :runtime
|
133
133
|
prerelease: false
|
134
|
-
version_requirements: *
|
134
|
+
version_requirements: *70301036161100
|
135
135
|
description: Cobweb is a web crawler that can use resque to cluster crawls to quickly
|
136
136
|
crawl extremely large sites which is much more perofmant than multi-threaded crawlers. It
|
137
137
|
is also a standalone crawler that has a sophisticated statistics monitoring interface
|
@@ -143,6 +143,7 @@ extra_rdoc_files:
|
|
143
143
|
- README.textile
|
144
144
|
files:
|
145
145
|
- spec/cobweb/cobweb_crawl_helper_spec.rb
|
146
|
+
- spec/cobweb/cobweb_crawl_spec.rb
|
146
147
|
- spec/cobweb/cobweb_crawler_spec.rb
|
147
148
|
- spec/cobweb/cobweb_job_spec.rb
|
148
149
|
- spec/cobweb/cobweb_links_spec.rb
|