cobweb 1.0.8 → 1.0.9
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 -1
- data/lib/cobweb_crawler.rb +1 -1
- data/lib/cobweb_links.rb +4 -0
- data/lib/cobweb_version.rb +1 -1
- metadata +24 -24
data/README.textile
CHANGED
data/lib/cobweb.rb
CHANGED
@@ -42,6 +42,7 @@ class Cobweb
|
|
42
42
|
default_timeout_to 10
|
43
43
|
default_redis_options_to Hash.new
|
44
44
|
default_internal_urls_to []
|
45
|
+
default_external_urls_to []
|
45
46
|
default_first_page_redirect_internal_to true
|
46
47
|
default_text_mime_types_to ["text/*", "application/xhtml+xml"]
|
47
48
|
default_obey_robots_to false
|
@@ -49,7 +50,7 @@ class Cobweb
|
|
49
50
|
default_valid_mime_types_to ["*/*"]
|
50
51
|
default_raise_exceptions_to false
|
51
52
|
default_store_refered_url_to false
|
52
|
-
|
53
|
+
|
53
54
|
end
|
54
55
|
|
55
56
|
# This method starts the resque based crawl and enqueues the base_url
|
data/lib/cobweb_crawler.rb
CHANGED
@@ -101,7 +101,7 @@ class CobwebCrawler
|
|
101
101
|
# select the link if its internal (eliminate external before expensive lookups in queued and crawled)
|
102
102
|
cobweb_links = CobwebLinks.new(@options)
|
103
103
|
|
104
|
-
internal_links = internal_links.select{|link| cobweb_links.internal?(link) || (@options[:crawl_linked_external] && cobweb_links.internal?(url.to_s))}
|
104
|
+
internal_links = internal_links.select{|link| cobweb_links.internal?(link) || (@options[:crawl_linked_external] && cobweb_links.internal?(url.to_s) && !cobweb_links.matches_external?(link))}
|
105
105
|
|
106
106
|
all_internal_links = internal_links
|
107
107
|
|
data/lib/cobweb_links.rb
CHANGED
@@ -35,6 +35,10 @@ class CobwebLinks
|
|
35
35
|
def external?(link)
|
36
36
|
@internal_patterns.select{|pattern| link.match(pattern)}.empty? || !@external_patterns.select{|pattern| link.match(pattern)}.empty?
|
37
37
|
end
|
38
|
+
|
39
|
+
def matches_external?(link)
|
40
|
+
!@external_patterns.select{|pattern| link.match(pattern)}.empty?
|
41
|
+
end
|
38
42
|
|
39
43
|
end
|
40
44
|
|
data/lib/cobweb_version.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: 1.0.
|
4
|
+
version: 1.0.9
|
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: 2013-02-
|
12
|
+
date: 2013-02-14 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70315669563580 !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: *70315669563580
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70315669557780 !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: *70315669557780
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70315669553860 !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: *70315669553860
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70315669550620 !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: *70315669550620
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70315669548760 !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: *70315669548760
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70315669546580 !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: *70315669546580
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70315669542520 !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: *70315669542520
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70315669538180 !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: *70315669538180
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70315669533960 !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: *70315669533960
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70315669528800 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,10 +120,10 @@ dependencies:
|
|
120
120
|
version: '0'
|
121
121
|
type: :runtime
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70315669528800
|
124
124
|
- !ruby/object:Gem::Dependency
|
125
125
|
name: json
|
126
|
-
requirement: &
|
126
|
+
requirement: &70315669525400 !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: *70315669525400
|
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 performant than multi-threaded crawlers. It
|
137
137
|
is also a standalone crawler that has a sophisticated statistics monitoring interface
|