cobweb 0.0.29 → 0.0.30

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.
Files changed (3) hide show
  1. data/README.textile +1 -1
  2. data/lib/cobweb.rb +7 -2
  3. metadata +20 -20
data/README.textile CHANGED
@@ -1,5 +1,5 @@
1
1
 
2
- h1. Cobweb v0.0.29
2
+ h1. Cobweb v0.0.30
3
3
 
4
4
  h2. Intro
5
5
 
data/lib/cobweb.rb CHANGED
@@ -19,7 +19,7 @@ class Cobweb
19
19
  # investigate using event machine for single threaded crawling
20
20
 
21
21
  def self.version
22
- "0.0.29"
22
+ "0.0.30"
23
23
  end
24
24
 
25
25
  def method_missing(method_sym, *arguments, &block)
@@ -103,6 +103,8 @@ class Cobweb
103
103
  uri = Addressable::URI.parse(url.strip)
104
104
 
105
105
  # retrieve data
106
+ ap uri.host
107
+ ap uri.inferred_port
106
108
  unless @http && @http.address == uri.host && @http.port == uri.inferred_port
107
109
  puts "Creating connection to #{uri.host}..." unless @options[:quiet]
108
110
  @http = Net::HTTP.new(uri.host, uri.inferred_port)
@@ -112,6 +114,7 @@ class Cobweb
112
114
  @http.verify_mode = OpenSSL::SSL::VERIFY_NONE
113
115
  end
114
116
 
117
+ ap uri.request_uri
115
118
  request_time = Time.now.to_f
116
119
  @http.read_timeout = @options[:timeout].to_i
117
120
  @http.open_timeout = @options[:timeout].to_i
@@ -125,7 +128,9 @@ class Cobweb
125
128
  puts "redirected... " unless @options[:quiet]
126
129
 
127
130
  # get location to redirect to
128
- url = Addressable::URI.parse(response['location']).to_s
131
+ ap "redirecting to #{response['location']}"
132
+ url = Addressable::URI.join(uri, response['location']).to_s
133
+ ap url
129
134
 
130
135
  # decrement redirect limit
131
136
  redirect_limit = redirect_limit - 1
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: 0.0.29
4
+ version: 0.0.30
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: 2012-03-14 00:00:00.000000000 Z
12
+ date: 2012-03-15 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: resque
16
- requirement: &70189333520340 !ruby/object:Gem::Requirement
16
+ requirement: &70105794152620 !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: *70189333520340
24
+ version_requirements: *70105794152620
25
25
  - !ruby/object:Gem::Dependency
26
26
  name: redis
27
- requirement: &70189333519900 !ruby/object:Gem::Requirement
27
+ requirement: &70105794152180 !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: *70189333519900
35
+ version_requirements: *70105794152180
36
36
  - !ruby/object:Gem::Dependency
37
37
  name: nokogiri
38
- requirement: &70189333519480 !ruby/object:Gem::Requirement
38
+ requirement: &70105794151760 !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: *70189333519480
46
+ version_requirements: *70105794151760
47
47
  - !ruby/object:Gem::Dependency
48
48
  name: addressable
49
- requirement: &70189333519060 !ruby/object:Gem::Requirement
49
+ requirement: &70105794151340 !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: *70189333519060
57
+ version_requirements: *70105794151340
58
58
  - !ruby/object:Gem::Dependency
59
59
  name: rspec
60
- requirement: &70189333518640 !ruby/object:Gem::Requirement
60
+ requirement: &70105794150920 !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: *70189333518640
68
+ version_requirements: *70105794150920
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: awesome_print
71
- requirement: &70189333518220 !ruby/object:Gem::Requirement
71
+ requirement: &70105794150500 !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: *70189333518220
79
+ version_requirements: *70105794150500
80
80
  - !ruby/object:Gem::Dependency
81
81
  name: sinatra
82
- requirement: &70189333517800 !ruby/object:Gem::Requirement
82
+ requirement: &70105794166440 !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: *70189333517800
90
+ version_requirements: *70105794166440
91
91
  - !ruby/object:Gem::Dependency
92
92
  name: thin
93
- requirement: &70189333517380 !ruby/object:Gem::Requirement
93
+ requirement: &70105794166020 !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: *70189333517380
101
+ version_requirements: *70105794166020
102
102
  - !ruby/object:Gem::Dependency
103
103
  name: haml
104
- requirement: &70189333533320 !ruby/object:Gem::Requirement
104
+ requirement: &70105794165600 !ruby/object:Gem::Requirement
105
105
  none: false
106
106
  requirements:
107
107
  - - ! '>='
@@ -109,7 +109,7 @@ dependencies:
109
109
  version: '0'
110
110
  type: :runtime
111
111
  prerelease: false
112
- version_requirements: *70189333533320
112
+ version_requirements: *70105794165600
113
113
  description: Web Crawler that uses resque background job engine to allow you to cluster
114
114
  your crawl.
115
115
  email: stewart@rockwellcottage.com