cobweb 0.0.36 → 0.0.37
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.rb +2 -2
- data/lib/crawl_job.rb +15 -4
- data/lib/encoding_safe_process_job.rb +13 -0
- metadata +23 -22
data/README.textile
CHANGED
data/lib/cobweb.rb
CHANGED
|
@@ -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.
|
|
23
|
+
"0.0.37"
|
|
24
24
|
end
|
|
25
25
|
|
|
26
26
|
def method_missing(method_sym, *arguments, &block)
|
|
@@ -34,7 +34,7 @@ class Cobweb
|
|
|
34
34
|
|
|
35
35
|
def initialize(options = {})
|
|
36
36
|
@options = options
|
|
37
|
-
|
|
37
|
+
default_use_encoding_safe_process_job_to false
|
|
38
38
|
default_follow_redirects_to true
|
|
39
39
|
default_redirect_limit_to 10
|
|
40
40
|
default_processing_queue_to CobwebProcessJob
|
data/lib/crawl_job.rb
CHANGED
|
@@ -52,9 +52,7 @@ class CrawlJob
|
|
|
52
52
|
end
|
|
53
53
|
|
|
54
54
|
# enqueue to processing queue
|
|
55
|
-
|
|
56
|
-
puts "#{content_request[:url]} has been sent for processing." if content_request[:debug]
|
|
57
|
-
puts "Crawled: #{@crawl_counter} Limit: #{content_request[:crawl_limit]} Queued: #{@queue_counter}" if content_request[:debug]
|
|
55
|
+
send_to_processing_queue(content, content_request)
|
|
58
56
|
|
|
59
57
|
#if the enqueue counter has been requested update that
|
|
60
58
|
if content_request.has_key? :enqueue_counter_key
|
|
@@ -63,7 +61,7 @@ class CrawlJob
|
|
|
63
61
|
enqueue_redis.hset(content_request[:enqueue_counter_key], content_request[:enqueue_counter_field], current_count+1)
|
|
64
62
|
end
|
|
65
63
|
|
|
66
|
-
# if
|
|
64
|
+
# if there's nothing left queued or the crawled limit has been reached
|
|
67
65
|
if @queue_counter == 0 || @crawl_counter >= content_request[:crawl_limit].to_i
|
|
68
66
|
|
|
69
67
|
# finished
|
|
@@ -86,6 +84,19 @@ class CrawlJob
|
|
|
86
84
|
|
|
87
85
|
end
|
|
88
86
|
|
|
87
|
+
def self.send_to_processing_queue(content, content_request)
|
|
88
|
+
content_to_send = content.merge({:internal_urls => internal_patterns, :redis_options => content_request[:redis_options], :source_id => content_request[:source_id], :crawl_id => content_request[:crawl_id]})
|
|
89
|
+
if content_request[:use_encoding_safe_process_job]
|
|
90
|
+
content_to_send[:body] = Base64.encode64(content[:body])
|
|
91
|
+
content_to_send[:processing_queue] = content_request[:processing_queue]
|
|
92
|
+
Resque.enqueue(EncodingSafeProcessJob, content_to_send)
|
|
93
|
+
else
|
|
94
|
+
Resque.enqueue(const_get(content_request[:processing_queue]), content_to_send)
|
|
95
|
+
end
|
|
96
|
+
puts "#{content_request[:url]} has been sent for processing. use_encoding_safe_process_job: #{content_request[:use_encoding_safe_process_job]}" if content_request[:debug]
|
|
97
|
+
puts "Crawled: #{@crawl_counter} Limit: #{content_request[:crawl_limit]} Queued: #{@queue_counter}" if content_request[:debug]
|
|
98
|
+
end
|
|
99
|
+
|
|
89
100
|
private
|
|
90
101
|
|
|
91
102
|
def self.within_crawl_limits?(crawl_limit)
|
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: 0.0.37
|
|
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: 2012-04-
|
|
12
|
+
date: 2012-04-24 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: resque
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &70275220162200 !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: *70275220162200
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: redis
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &70275220161740 !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: *70275220161740
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: nokogiri
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &70275220177640 !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: *70275220177640
|
|
47
47
|
- !ruby/object:Gem::Dependency
|
|
48
48
|
name: addressable
|
|
49
|
-
requirement: &
|
|
49
|
+
requirement: &70275220177220 !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: *70275220177220
|
|
58
58
|
- !ruby/object:Gem::Dependency
|
|
59
59
|
name: rspec
|
|
60
|
-
requirement: &
|
|
60
|
+
requirement: &70275220176640 !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: *70275220176640
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: awesome_print
|
|
71
|
-
requirement: &
|
|
71
|
+
requirement: &70275220176220 !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: *70275220176220
|
|
80
80
|
- !ruby/object:Gem::Dependency
|
|
81
81
|
name: sinatra
|
|
82
|
-
requirement: &
|
|
82
|
+
requirement: &70275220175780 !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: *70275220175780
|
|
91
91
|
- !ruby/object:Gem::Dependency
|
|
92
92
|
name: thin
|
|
93
|
-
requirement: &
|
|
93
|
+
requirement: &70275220175360 !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: *70275220175360
|
|
102
102
|
- !ruby/object:Gem::Dependency
|
|
103
103
|
name: haml
|
|
104
|
-
requirement: &
|
|
104
|
+
requirement: &70275220174940 !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: *70275220174940
|
|
113
113
|
- !ruby/object:Gem::Dependency
|
|
114
114
|
name: namespaced_redis
|
|
115
|
-
requirement: &
|
|
115
|
+
requirement: &70275220174520 !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: *
|
|
123
|
+
version_requirements: *70275220174520
|
|
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
|
|
@@ -141,6 +141,7 @@ files:
|
|
|
141
141
|
- lib/cobweb_process_job.rb
|
|
142
142
|
- lib/content_link_parser.rb
|
|
143
143
|
- lib/crawl_job.rb
|
|
144
|
+
- lib/encoding_safe_process_job.rb
|
|
144
145
|
- lib/redirect_error.rb
|
|
145
146
|
- lib/robots.rb
|
|
146
147
|
- lib/stats.rb
|