cobweb 0.0.76 → 0.0.77
Sign up to get free protection for your applications and to get access to all the features.
- data/README.textile +1 -1
- data/lib/cobweb_version.rb +1 -1
- data/lib/crawl.rb +26 -27
- data/lib/crawl_job.rb +17 -19
- data/spec/cobweb/cobweb_job_spec.rb +0 -6
- metadata +25 -25
data/README.textile
CHANGED
data/lib/cobweb_version.rb
CHANGED
data/lib/crawl.rb
CHANGED
@@ -50,37 +50,35 @@ module CobwebModule
|
|
50
50
|
end
|
51
51
|
|
52
52
|
def retrieve
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
update_queues
|
53
|
+
unless @redis.sismember("currently_running", @options[:url])
|
54
|
+
@redis.sadd("currently_running", @options[:url])
|
55
|
+
unless already_crawled?
|
56
|
+
if within_crawl_limits?
|
57
|
+
@stats.update_status("Retrieving #{@options[:url]}...")
|
58
|
+
@content = Cobweb.new(@options).get(@options[:url], @options)
|
59
|
+
if @options[:url] == @redis.get("original_base_url")
|
60
|
+
@redis.set("crawled_base_url", @content[:base_url])
|
61
|
+
end
|
62
|
+
update_queues
|
64
63
|
|
65
|
-
|
66
|
-
|
64
|
+
if content.permitted_type?
|
65
|
+
## update statistics
|
67
66
|
|
68
|
-
|
69
|
-
|
70
|
-
end
|
71
|
-
else
|
72
|
-
decrement_queue_counter
|
67
|
+
@stats.update_statistics(@content)
|
68
|
+
return true
|
73
69
|
end
|
74
70
|
else
|
75
71
|
decrement_queue_counter
|
76
72
|
end
|
77
73
|
else
|
78
|
-
debug_puts "\n\nDETECTED DUPLICATE JOB for #{@options[:url]}\n"
|
79
|
-
debug_ap @redis.smembers("currently_running")
|
80
74
|
decrement_queue_counter
|
81
75
|
end
|
82
|
-
|
76
|
+
else
|
77
|
+
debug_puts "\n\nDETECTED DUPLICATE JOB for #{@options[:url]}\n"
|
78
|
+
debug_ap @redis.smembers("currently_running")
|
79
|
+
decrement_queue_counter
|
83
80
|
end
|
81
|
+
false
|
84
82
|
end
|
85
83
|
|
86
84
|
def process_links &block
|
@@ -156,7 +154,7 @@ module CobwebModule
|
|
156
154
|
increment_process_counter
|
157
155
|
end
|
158
156
|
@redis.sadd "enqueued", @options[:url]
|
159
|
-
|
157
|
+
|
160
158
|
yield if block_given?
|
161
159
|
@redis.incr("crawl_job_enqueued_count")
|
162
160
|
end
|
@@ -181,7 +179,7 @@ module CobwebModule
|
|
181
179
|
end
|
182
180
|
|
183
181
|
def finished
|
184
|
-
set_first_to_finish
|
182
|
+
set_first_to_finish
|
185
183
|
debug_ap "CRAWL FINISHED #{@options[:url]}, #{counters}, #{@redis.get("original_base_url")}, #{@redis.get("crawled_base_url")}"
|
186
184
|
@stats.end_crawl(@options)
|
187
185
|
end
|
@@ -204,7 +202,7 @@ module CobwebModule
|
|
204
202
|
def first_to_finish?
|
205
203
|
@first_to_finish
|
206
204
|
end
|
207
|
-
|
205
|
+
|
208
206
|
def crawled_base_url
|
209
207
|
@redis.get("crawled_base_url")
|
210
208
|
end
|
@@ -228,6 +226,7 @@ module CobwebModule
|
|
228
226
|
end
|
229
227
|
|
230
228
|
debug_puts "RECEIVED LOCK [#{key}]"
|
229
|
+
@redis.expire("#{key}_lock", 10)
|
231
230
|
begin
|
232
231
|
result = yield
|
233
232
|
ensure
|
@@ -236,15 +235,15 @@ module CobwebModule
|
|
236
235
|
end
|
237
236
|
result
|
238
237
|
end
|
239
|
-
|
238
|
+
|
240
239
|
def debug_ap(value)
|
241
240
|
ap(value) if @options[:debug]
|
242
241
|
end
|
243
|
-
|
242
|
+
|
244
243
|
def debug_puts(value)
|
245
244
|
puts(value) if @options[:debug]
|
246
245
|
end
|
247
|
-
|
246
|
+
|
248
247
|
private
|
249
248
|
def setup_defaults
|
250
249
|
@options[:redis_options] = {} unless @options.has_key? :redis_options
|
data/lib/crawl_job.rb
CHANGED
@@ -29,30 +29,28 @@ class CrawlJob
|
|
29
29
|
|
30
30
|
end
|
31
31
|
|
32
|
-
@crawl.
|
33
|
-
|
34
|
-
|
35
|
-
@crawl.process do
|
32
|
+
if @crawl.to_be_processed?
|
33
|
+
|
34
|
+
@crawl.process do
|
36
35
|
|
37
|
-
|
38
|
-
|
39
|
-
|
36
|
+
# enqueue to processing queue
|
37
|
+
@crawl.debug_puts "ENQUEUED [#{@crawl.redis.get("crawl_job_enqueued_count")}] URL: #{@crawl.content.url}"
|
38
|
+
send_to_processing_queue(@crawl.content.to_hash, content_request)
|
40
39
|
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
end
|
47
|
-
|
40
|
+
#if the enqueue counter has been requested update that
|
41
|
+
if content_request.has_key?(:enqueue_counter_key)
|
42
|
+
enqueue_redis = Redis::Namespace.new(content_request[:enqueue_counter_namespace].to_s, :redis => Redis.new(content_request[:redis_options]))
|
43
|
+
current_count = enqueue_redis.hget(content_request[:enqueue_counter_key], content_request[:enqueue_counter_field]).to_i
|
44
|
+
enqueue_redis.hset(content_request[:enqueue_counter_key], content_request[:enqueue_counter_field], current_count+1)
|
48
45
|
end
|
49
|
-
|
50
|
-
@crawl.debug_puts "@crawl.finished? #{@crawl.finished?}"
|
51
|
-
@crawl.debug_puts "@crawl.within_crawl_limits? #{@crawl.within_crawl_limits?}"
|
52
|
-
@crawl.debug_puts "@crawl.first_to_finish? #{@crawl.first_to_finish?}"
|
46
|
+
|
53
47
|
end
|
54
|
-
|
48
|
+
else
|
49
|
+
@crawl.debug_puts "@crawl.finished? #{@crawl.finished?}"
|
50
|
+
@crawl.debug_puts "@crawl.within_crawl_limits? #{@crawl.within_crawl_limits?}"
|
51
|
+
@crawl.debug_puts "@crawl.first_to_finish? #{@crawl.first_to_finish?}"
|
55
52
|
end
|
53
|
+
|
56
54
|
end
|
57
55
|
end
|
58
56
|
|
@@ -262,16 +262,10 @@ def running?(crawl_id)
|
|
262
262
|
else
|
263
263
|
if status == @last_stat
|
264
264
|
if @counter > 20
|
265
|
-
puts ""
|
266
265
|
raise "Static status: #{status}"
|
267
266
|
else
|
268
267
|
@counter += 1
|
269
268
|
end
|
270
|
-
if @counter == 1
|
271
|
-
print "Static Status.. #{21-@counter}"
|
272
|
-
else
|
273
|
-
print ".#{21-@counter}"
|
274
|
-
end
|
275
269
|
else
|
276
270
|
result = status != CobwebCrawlHelper::FINISHED && status != CobwebCrawlHelper::CANCELLED
|
277
271
|
end
|
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: 0.0.77
|
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: 2012-10-24 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70355025183680 !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: *70355025183680
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70355025182000 !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: *70355025182000
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70355025180660 !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: *70355025180660
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70355025179740 !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: *70355025179740
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70355025179160 !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: *70355025179160
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70355025178560 !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: *70355025178560
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70355025177760 !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: *70355025177760
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70355025177180 !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: *70355025177180
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70355025176740 !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: *70355025176740
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70355025175980 !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: *70355025175980
|
124
124
|
- !ruby/object:Gem::Dependency
|
125
125
|
name: json
|
126
|
-
requirement: &
|
126
|
+
requirement: &70355025175280 !ruby/object:Gem::Requirement
|
127
127
|
none: false
|
128
128
|
requirements:
|
129
129
|
- - ! '>='
|
@@ -131,9 +131,9 @@ dependencies:
|
|
131
131
|
version: '0'
|
132
132
|
type: :runtime
|
133
133
|
prerelease: false
|
134
|
-
version_requirements: *
|
134
|
+
version_requirements: *70355025175280
|
135
135
|
description: Cobweb is a web crawler that can use resque to cluster crawls to quickly
|
136
|
-
crawl extremely large sites which is much more
|
136
|
+
crawl extremely large sites which is much more performant than multi-threaded crawlers. It
|
137
137
|
is also a standalone crawler that has a sophisticated statistics monitoring interface
|
138
138
|
to monitor the progress of the crawls.
|
139
139
|
email: stewart@rockwellcottage.com
|