krawler 1.0.13 → 1.0.14
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/lib/krawler.rb +8 -2
- data/lib/krawler/version.rb +1 -1
- metadata +5 -10
data/lib/krawler.rb
CHANGED
@@ -112,7 +112,7 @@ module Krawler
|
|
112
112
|
@mutex.synchronize do
|
113
113
|
return if !page.respond_to?(:links)
|
114
114
|
|
115
|
-
recache_invalid_results(page)
|
115
|
+
#recache_invalid_results(page)
|
116
116
|
|
117
117
|
page.links.each do |new_link|
|
118
118
|
next if new_link.href.nil?
|
@@ -168,7 +168,13 @@ module Krawler
|
|
168
168
|
query = params_to_hash(uri.query || '')
|
169
169
|
query['cache'] = 'false'
|
170
170
|
uri.query = hash_to_params(query)
|
171
|
-
@
|
171
|
+
if @restrict # don't crawl outside of our restricted base path
|
172
|
+
if @include && uri.path =~ /#{@include}/ # unless we match our inclusion
|
173
|
+
if !@crawled_links.include?(uri.path) && !@links_to_crawl.include?(uri.path) # don't crawl what we've alread crawled
|
174
|
+
@links_to_crawl << uri.to_s
|
175
|
+
end
|
176
|
+
end
|
177
|
+
end
|
172
178
|
end
|
173
179
|
end
|
174
180
|
end
|
data/lib/krawler/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: krawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.14
|
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:
|
12
|
+
date: 2013-03-19 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mechanize
|
16
|
-
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirement: &70187441725840 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,12 +21,7 @@ dependencies:
|
|
21
21
|
version: 2.5.1
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements:
|
25
|
-
none: false
|
26
|
-
requirements:
|
27
|
-
- - ~>
|
28
|
-
- !ruby/object:Gem::Version
|
29
|
-
version: 2.5.1
|
24
|
+
version_requirements: *70187441725840
|
30
25
|
description: Simple little website crawler.
|
31
26
|
email:
|
32
27
|
- mike@urlgonomics.com
|
@@ -66,7 +61,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
66
61
|
version: '0'
|
67
62
|
requirements: []
|
68
63
|
rubyforge_project: krawler
|
69
|
-
rubygems_version: 1.8.
|
64
|
+
rubygems_version: 1.8.17
|
70
65
|
signing_key:
|
71
66
|
specification_version: 3
|
72
67
|
summary: ''
|