krawler 1.0.0 → 1.0.1
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/version.rb +1 -1
- data/lib/krawler.rb +4 -3
- metadata +4 -4
data/lib/krawler/version.rb
CHANGED
data/lib/krawler.rb
CHANGED
|
@@ -77,17 +77,18 @@ module Krawler
|
|
|
77
77
|
@suspect_links << link
|
|
78
78
|
return
|
|
79
79
|
ensure
|
|
80
|
-
@mutex.synchronize
|
|
80
|
+
@mutex.synchronize do
|
|
81
81
|
puts link
|
|
82
82
|
puts " [#{Time.now - start}s] #{@links_to_crawl.size} links..."
|
|
83
|
-
|
|
83
|
+
end
|
|
84
84
|
end
|
|
85
85
|
|
|
86
86
|
@mutex.synchronize do
|
|
87
87
|
return if !page.respond_to?(:links)
|
|
88
88
|
page.links.each do |new_link|
|
|
89
89
|
next if new_link.href.nil?
|
|
90
|
-
|
|
90
|
+
next if new_link.rel.include? 'nofollow'
|
|
91
|
+
|
|
91
92
|
# quick scrub known issues
|
|
92
93
|
new_link = new_link.href.gsub(/ /, '%20')
|
|
93
94
|
|
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: 1.0.1
|
|
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-
|
|
12
|
+
date: 2012-06-28 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: mechanize
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &70152297970740 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ~>
|
|
@@ -21,7 +21,7 @@ dependencies:
|
|
|
21
21
|
version: 2.5.0
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *70152297970740
|
|
25
25
|
description: Simple little website crawler.
|
|
26
26
|
email:
|
|
27
27
|
- mike@urlgonomics.com
|