cobweb 0.0.71 → 0.0.72
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_crawl_helper.rb +22 -9
- data/lib/cobweb_version.rb +1 -1
- data/lib/stats.rb +5 -2
- metadata +24 -24
data/README.textile
CHANGED
data/lib/cobweb_crawl_helper.rb
CHANGED
@@ -10,28 +10,41 @@ class CobwebCrawlHelper
|
|
10
10
|
|
11
11
|
def initialize(data)
|
12
12
|
@data = data
|
13
|
+
|
14
|
+
# TAKING A LONG TIME TO RUN ON PRODUCTION BOX
|
13
15
|
@stats = Stats.new(data)
|
14
16
|
end
|
15
17
|
|
16
|
-
def destroy
|
17
|
-
|
18
|
+
def destroy(options)
|
19
|
+
|
20
|
+
options[:queue_name] = "cobweb_crawl_job" unless options.has_key?(:queue_name)
|
21
|
+
options[:finished_resque_queue] = CobwebFinishedJob unless options.has_key?(:finished_resque_queue)
|
22
|
+
|
18
23
|
# set status as cancelled now so that we don't enqueue any further pages
|
19
24
|
self.statistics.end_crawl(@data, true)
|
25
|
+
puts "end_crawl: #{self.statistics.get_status}"
|
26
|
+
if options[:finished_resque_queue]
|
27
|
+
puts "enqueueing finished job..."
|
28
|
+
|
29
|
+
additional_stats = {:crawl_id => id, :crawled_base_url => @stats.redis.get("crawled_base_url")}
|
30
|
+
additional_stats[:redis_options] = @data[:redis_options] unless @data[:redis_options] == {}
|
31
|
+
additional_stats[:source_id] = options[:source_id] unless options[:source_id].nil?
|
32
|
+
|
33
|
+
Resque.enqueue(options[:finished_resque_queue], @stats.get_statistics.merge(additional_stats))
|
34
|
+
end
|
20
35
|
|
21
|
-
|
22
|
-
|
36
|
+
position = 0
|
37
|
+
job_items = Resque.peek(options[:queue_name], position, BATCH_SIZE)
|
23
38
|
until job_items.empty?
|
24
|
-
|
39
|
+
puts "Batch: #{position} : #{job_items.count}"
|
25
40
|
job_items.each do |item|
|
26
41
|
if item["args"][0]["crawl_id"] == id
|
27
|
-
#
|
42
|
+
# remove this job from the queue
|
28
43
|
Resque.dequeue(CrawlJob, item["args"][0])
|
29
44
|
end
|
30
45
|
end
|
31
46
|
|
32
|
-
|
33
|
-
batch_count += 1
|
34
|
-
job_items = Resque.peek(queue_name, position, BATCH_SIZE)
|
47
|
+
job_items = Resque.peek(options[:queue_name], position+=BATCH_SIZE, BATCH_SIZE)
|
35
48
|
end
|
36
49
|
|
37
50
|
end
|
data/lib/cobweb_version.rb
CHANGED
data/lib/stats.rb
CHANGED
@@ -1,6 +1,9 @@
|
|
1
1
|
# Stats class is the main statisitics hub for monitoring crawls. Either can be viewed through the Sinatra interface, or returned from the CobwebCrawler.crawl method or block
|
2
2
|
class Stats
|
3
3
|
require 'json'
|
4
|
+
|
5
|
+
attr_reader :redis
|
6
|
+
|
4
7
|
# Sets up redis usage for statistics
|
5
8
|
def initialize(options)
|
6
9
|
options[:redis_options] = {} unless options.has_key? :redis_options
|
@@ -131,7 +134,7 @@ class Stats
|
|
131
134
|
@statistics[:status_counts] = status_counts.to_json
|
132
135
|
|
133
136
|
## time based statistics
|
134
|
-
increment_time_stat("minute_totals", "minute", 60)
|
137
|
+
increment_time_stat("minute_totals", "minute", 60)
|
135
138
|
|
136
139
|
redis_command = "@redis.hmset 'statistics', #{@statistics.keys.map{|key| "'#{key}', '#{@statistics[key].to_s.gsub("'","''")}'"}.join(", ")}"
|
137
140
|
instance_eval redis_command
|
@@ -158,7 +161,7 @@ class Stats
|
|
158
161
|
|
159
162
|
# Sets the current status of the crawl
|
160
163
|
def update_status(status)
|
161
|
-
|
164
|
+
@redis.hset("statistics", "current_status", status) unless get_status == CobwebCrawlHelper::CANCELLED
|
162
165
|
end
|
163
166
|
|
164
167
|
# Returns the current status of the crawl
|
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: 0.0.72
|
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: 2012-09-
|
12
|
+
date: 2012-09-20 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70308627743380 !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: *70308627743380
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70308627741840 !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: *70308627741840
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70308627741060 !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: *70308627741060
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70308627740200 !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: *70308627740200
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70308627739500 !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: *70308627739500
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70308627739020 !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: *70308627739020
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70308627738100 !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: *70308627738100
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70308627737580 !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: *70308627737580
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70308627737040 !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: *70308627737040
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70308627736400 !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: *70308627736400
|
124
124
|
- !ruby/object:Gem::Dependency
|
125
125
|
name: json
|
126
|
-
requirement: &
|
126
|
+
requirement: &70308627735860 !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: *70308627735860
|
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
|