cobweb 0.0.62 → 0.0.63
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_links.rb +0 -16
- data/lib/cobweb_version.rb +1 -1
- data/lib/crawl_job.rb +13 -13
- data/lib/stats.rb +1 -1
- data/spec/cobweb/cobweb_job_spec.rb +1 -1
- data/views/layout.haml +3 -3
- metadata +22 -22
data/README.textile
CHANGED
data/lib/cobweb_links.rb
CHANGED
@@ -28,27 +28,11 @@ class CobwebLinks
|
|
28
28
|
|
29
29
|
# Returns true if the link is matched to an internal_url and not matched to an external_url
|
30
30
|
def internal?(link)
|
31
|
-
if @options[:debug]
|
32
|
-
puts "--------------------------------"
|
33
|
-
puts "Link: #{link}"
|
34
|
-
puts "Internal matches"
|
35
|
-
ap @internal_patterns.select{|pattern| link.match(pattern)}
|
36
|
-
puts "External matches"
|
37
|
-
ap @external_patterns.select{|pattern| link.match(pattern)}
|
38
|
-
end
|
39
31
|
!@internal_patterns.select{|pattern| link.match(pattern)}.empty? && @external_patterns.select{|pattern| link.match(pattern)}.empty?
|
40
32
|
end
|
41
33
|
|
42
34
|
# Returns true if the link is matched to an external_url or not matched to an internal_url
|
43
35
|
def external?(link)
|
44
|
-
if @options[:debug]
|
45
|
-
puts "--------------------------------"
|
46
|
-
puts "Link: #{link}"
|
47
|
-
puts "Internal matches"
|
48
|
-
ap @internal_patterns.select{|pattern| link.match(pattern)}
|
49
|
-
puts "External matches"
|
50
|
-
ap @external_patterns.select{|pattern| link.match(pattern)}
|
51
|
-
end
|
52
36
|
@internal_patterns.select{|pattern| link.match(pattern)}.empty? || !@external_patterns.select{|pattern| link.match(pattern)}.empty?
|
53
37
|
end
|
54
38
|
|
data/lib/cobweb_version.rb
CHANGED
data/lib/crawl_job.rb
CHANGED
@@ -28,14 +28,14 @@ class CrawlJob
|
|
28
28
|
|
29
29
|
# check we haven't crawled this url before
|
30
30
|
unless @redis.sismember "crawled", content_request[:url]
|
31
|
-
|
32
|
-
if content_request[:
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
if
|
31
|
+
# if there is no limit or we're still under it lets get the url
|
32
|
+
if within_crawl_limits?(content_request[:crawl_limit])
|
33
|
+
content = Cobweb.new(content_request).get(content_request[:url], content_request)
|
34
|
+
if content_request[:url] == @redis.get("original_base_url")
|
35
|
+
puts content
|
36
|
+
@redis.set("crawled_base_url", content[:base_url])
|
37
|
+
end
|
38
|
+
if is_permitted_type(content)
|
39
39
|
begin
|
40
40
|
# move the url from the queued list to the crawled list - for both the original url, and the content url (to handle redirects)
|
41
41
|
@redis.srem "queued", content_request[:url]
|
@@ -99,10 +99,10 @@ class CrawlJob
|
|
99
99
|
puts "Crawled: #{@crawl_counter} Limit: #{content_request[:crawl_limit]} Queued: #{@queue_counter} In Progress: #{@crawl_started_counter-@crawl_counter}" if @debug
|
100
100
|
end
|
101
101
|
else
|
102
|
-
puts "ignoring #{content_request[:url]} as
|
102
|
+
puts "ignoring #{content_request[:url]} as mime_type is #{content[:mime_type]}" if content_request[:debug]
|
103
103
|
end
|
104
104
|
else
|
105
|
-
puts "ignoring #{content_request[:url]} as
|
105
|
+
puts "ignoring #{content_request[:url]} as outside of crawl limits." if content_request[:debug]
|
106
106
|
end
|
107
107
|
|
108
108
|
else
|
@@ -122,15 +122,15 @@ class CrawlJob
|
|
122
122
|
|
123
123
|
end
|
124
124
|
|
125
|
-
# Sets the crawl status to 'Crawl
|
125
|
+
# Sets the crawl status to 'Crawl Finished' and enqueues the crawl finished job
|
126
126
|
def self.finished(content_request)
|
127
127
|
# finished
|
128
|
-
if @redis.hget("statistics", "current_status")!= "Crawl
|
128
|
+
if @redis.hget("statistics", "current_status")!= "Crawl Finished"
|
129
129
|
ap "CRAWL FINISHED #{content_request[:url]}, #{counters}, #{@redis.get("original_base_url")}, #{@redis.get("crawled_base_url")}" if content_request[:debug]
|
130
130
|
@stats.end_crawl(content_request)
|
131
131
|
Resque.enqueue(const_get(content_request[:crawl_finished_queue]), @stats.get_statistics.merge({:redis_options => content_request[:redis_options], :crawl_id => content_request[:crawl_id], :source_id => content_request[:source_id], :crawled_base_url => @redis.get("crawled_base_url")}))
|
132
132
|
else
|
133
|
-
|
133
|
+
# nothing to report here, we're skipping the remaining urls as we're outside of the crawl limit
|
134
134
|
end
|
135
135
|
end
|
136
136
|
|
data/lib/stats.rb
CHANGED
@@ -23,7 +23,7 @@ class Stats
|
|
23
23
|
# Removes the crawl from the running crawls and updates status
|
24
24
|
def end_crawl(options)
|
25
25
|
@full_redis.srem "cobweb_crawls", options[:crawl_id]
|
26
|
-
@redis.hset "statistics", "current_status", "Crawl
|
26
|
+
@redis.hset "statistics", "current_status", "Crawl Finished"
|
27
27
|
@redis.del "crawl_details"
|
28
28
|
end
|
29
29
|
|
data/views/layout.haml
CHANGED
@@ -51,17 +51,17 @@
|
|
51
51
|
%ul
|
52
52
|
%li.home
|
53
53
|
%a{:href => "#"}
|
54
|
-
%li.break
|
54
|
+
%li.break >
|
55
55
|
%li
|
56
56
|
%a{:href => "#"} Menu item
|
57
|
-
%li.break
|
57
|
+
%li.break >
|
58
58
|
%li
|
59
59
|
%a{:href => "#"} Menu item
|
60
60
|
= yield
|
61
61
|
|
62
62
|
.footer
|
63
63
|
.split
|
64
|
-
|
64
|
+
Copyright
|
65
65
|
%a{:href => "http://www.activeinformationdesign.com"} activeinformationdesign.com
|
66
66
|
.split.right
|
67
67
|
Powered by
|
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: 0.0.63
|
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: 2012-07
|
12
|
+
date: 2012-08-07 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70236896384860 !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: *70236896384860
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70236896384380 !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: *70236896384380
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70236896383640 !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: *70236896383640
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70236896382560 !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: *70236896382560
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70236896381420 !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: *70236896381420
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70236896380260 !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: *70236896380260
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70236896395760 !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: *70236896395760
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70236896395220 !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: *70236896395220
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70236896394540 !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: *70236896394540
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70236896393840 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,7 +120,7 @@ dependencies:
|
|
120
120
|
version: 1.0.2
|
121
121
|
type: :runtime
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70236896393840
|
124
124
|
description: Cobweb is a web crawler that can use resque to cluster crawls to quickly
|
125
125
|
crawl extremely large sites which is much more perofmant than multi-threaded crawlers. It
|
126
126
|
is also a standalone crawler that has a sophisticated statistics monitoring interface
|