cobweb 0.0.21 → 0.0.22
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/cobweb.rb +18 -10
- data/lib/crawl_job.rb +4 -3
- data/lib/stats.rb +0 -1
- metadata +21 -21
data/lib/cobweb.rb
CHANGED
@@ -5,8 +5,8 @@ require "addressable/uri"
|
|
5
5
|
require 'digest/sha1'
|
6
6
|
require 'base64'
|
7
7
|
|
8
|
-
Dir[File.dirname(__FILE__) + '
|
9
|
-
require
|
8
|
+
Dir[File.dirname(__FILE__) + '/**/*.rb'].each do |file|
|
9
|
+
require file
|
10
10
|
end
|
11
11
|
|
12
12
|
class Cobweb
|
@@ -18,6 +18,10 @@ class Cobweb
|
|
18
18
|
# on end of crawl, return statistic hash (could call specified method ?) if single threaded or enqueue to a specified queue the stat hash
|
19
19
|
# investigate using event machine for single threaded crawling
|
20
20
|
|
21
|
+
def self.version
|
22
|
+
"0.0.22"
|
23
|
+
end
|
24
|
+
|
21
25
|
def initialize(options = {})
|
22
26
|
@options = options
|
23
27
|
@options[:follow_redirects] = true unless @options.has_key?(:follow_redirects)
|
@@ -34,12 +38,12 @@ class Cobweb
|
|
34
38
|
def start(base_url)
|
35
39
|
raise ":base_url is required" unless base_url
|
36
40
|
request = {
|
37
|
-
:crawl_id => Digest::SHA1.hexdigest(Time.now.
|
41
|
+
:crawl_id => Digest::SHA1.hexdigest("#{Time.now.to_i}.#{Time.now.usec}"),
|
38
42
|
:url => base_url
|
39
43
|
}
|
40
44
|
|
41
45
|
request.merge!(@options)
|
42
|
-
@redis = NamespacedRedis.new(Redis.new(request[:redis_options]), "cobweb-#{
|
46
|
+
@redis = NamespacedRedis.new(Redis.new(request[:redis_options]), "cobweb-#{Cobweb.version}-#{request[:crawl_id]}")
|
43
47
|
@redis.hset "statistics", "queued_at", DateTime.now
|
44
48
|
|
45
49
|
Resque.enqueue(CrawlJob, request)
|
@@ -53,13 +57,17 @@ class Cobweb
|
|
53
57
|
|
54
58
|
# get the unique id for this request
|
55
59
|
unique_id = Digest::SHA1.hexdigest(url.to_s)
|
56
|
-
redirect_limit
|
60
|
+
if options.has_key?(:redirect_limit) and !options[:redirect_limit].nil?
|
61
|
+
redirect_limit = options[:redirect_limit].to_i
|
62
|
+
else
|
63
|
+
redirect_limit = 10
|
64
|
+
end
|
57
65
|
|
58
66
|
# connect to redis
|
59
67
|
if options.has_key? :crawl_id
|
60
|
-
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{
|
68
|
+
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{Cobweb.version}-#{options[:crawl_id]}")
|
61
69
|
else
|
62
|
-
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{
|
70
|
+
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{Cobweb.version}")
|
63
71
|
end
|
64
72
|
|
65
73
|
content = {}
|
@@ -107,7 +115,7 @@ class Cobweb
|
|
107
115
|
raise RedirectError, "Redirect Limit reached" if redirect_limit == 0
|
108
116
|
|
109
117
|
# get the content from redirect location
|
110
|
-
content = get(url, redirect_limit)
|
118
|
+
content = get(url, options.merge(:redirect_limit => redirect_limit))
|
111
119
|
content[:url] = uri.to_s
|
112
120
|
content[:redirect_through] = [] if content[:redirect_through].nil?
|
113
121
|
content[:redirect_through].insert(0, url)
|
@@ -206,9 +214,9 @@ class Cobweb
|
|
206
214
|
|
207
215
|
# connect to redis
|
208
216
|
if options.has_key? :crawl_id
|
209
|
-
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{
|
217
|
+
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{Cobweb.version}-#{options[:crawl_id]}")
|
210
218
|
else
|
211
|
-
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{
|
219
|
+
redis = NamespacedRedis.new(Redis.new(@options[:redis_options]), "cobweb-#{Cobweb.version}")
|
212
220
|
end
|
213
221
|
|
214
222
|
content = {}
|
data/lib/crawl_job.rb
CHANGED
@@ -28,8 +28,8 @@ class CrawlJob
|
|
28
28
|
def self.perform(content_request)
|
29
29
|
# change all hash keys to symbols
|
30
30
|
content_request.deep_symbolize_keys
|
31
|
-
redis = NamespacedRedis.new(Redis.new(content_request[:redis_options]), "cobweb-#{
|
32
|
-
|
31
|
+
redis = NamespacedRedis.new(Redis.new(content_request[:redis_options]), "cobweb-#{Cobweb.version}-#{content_request[:crawl_id]}")
|
32
|
+
|
33
33
|
@absolutize = Absolutize.new(content_request[:url], :output_debug => false, :raise_exceptions => false, :force_escaping => false, :remove_anchors => true)
|
34
34
|
|
35
35
|
# check we haven't crawled this url before
|
@@ -95,6 +95,7 @@ class CrawlJob
|
|
95
95
|
redis.sadd "crawled", content_request[:url]
|
96
96
|
set_base_url redis, content, content_request[:base_url]
|
97
97
|
content[:links].keys.map{|key| content[:links][key]}.flatten.each do |link|
|
98
|
+
link = link.to_s
|
98
99
|
unless redis.sismember "crawled", link
|
99
100
|
puts "Checking if #{link} matches #{redis.get("base_url")} as internal?" if content_request[:debug]
|
100
101
|
if link.to_s.match(Regexp.new("^#{redis.get("base_url")}"))
|
@@ -129,7 +130,7 @@ class CrawlJob
|
|
129
130
|
|
130
131
|
# detect finished state
|
131
132
|
|
132
|
-
if queue_counter == crawl_counter or content_request[:crawl_limit].to_i <= crawl_counter
|
133
|
+
if queue_counter == crawl_counter or content_request[:crawl_limit].to_i <= crawl_counter
|
133
134
|
|
134
135
|
puts "queue_counter: #{queue_counter}"
|
135
136
|
puts "crawl_counter: #{crawl_counter}"
|
data/lib/stats.rb
CHANGED
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: 0.0.22
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2012-03-09 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70101145919340 !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: *70101145919340
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70101145918920 !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: *70101145918920
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: absolutize
|
38
|
-
requirement: &
|
38
|
+
requirement: &70101145918500 !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: *70101145918500
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: nokogiri
|
49
|
-
requirement: &
|
49
|
+
requirement: &70101145934440 !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: *70101145934440
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: addressable
|
60
|
-
requirement: &
|
60
|
+
requirement: &70101145934020 !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: *70101145934020
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: rspec
|
71
|
-
requirement: &
|
71
|
+
requirement: &70101145933580 !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: *70101145933580
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: awesome_print
|
82
|
-
requirement: &
|
82
|
+
requirement: &70101145933160 !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: *70101145933160
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: sinatra
|
93
|
-
requirement: &
|
93
|
+
requirement: &70101145932740 !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: *70101145932740
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: thin
|
104
|
-
requirement: &
|
104
|
+
requirement: &70101145932320 !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: *70101145932320
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: haml
|
115
|
-
requirement: &
|
115
|
+
requirement: &70101145931900 !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: *70101145931900
|
124
124
|
description:
|
125
125
|
email: stewart@rockwellcottage.com
|
126
126
|
executables: []
|