robotstxt 0.5.2 → 0.5.3
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/robotstxt.rb +2 -2
- data/lib/robotstxt/parser.rb +1 -1
- data/robotstxt.gemspec +2 -2
- metadata +2 -2
data/lib/robotstxt.rb
CHANGED
|
@@ -24,11 +24,11 @@ module Robotstxt
|
|
|
24
24
|
NAME = 'Robotstxt'
|
|
25
25
|
GEM = 'robotstxt'
|
|
26
26
|
AUTHORS = ['Simone Rinzivillo <srinzivillo@gmail.com>']
|
|
27
|
-
VERSION = '0.5.
|
|
27
|
+
VERSION = '0.5.3'
|
|
28
28
|
|
|
29
29
|
|
|
30
30
|
# Check if the <tt>URL</tt> is allowed to be crawled from the current <tt>Robot_id</tt>.
|
|
31
|
-
#
|
|
31
|
+
# Robotstxt::Allowed? returns <tt>true</tt> if the robots.txt file does not block the access to the URL.
|
|
32
32
|
#
|
|
33
33
|
# Robotstxt.allowed?('http://www.simonerinzivillo.it/', 'rubytest')
|
|
34
34
|
#
|
data/lib/robotstxt/parser.rb
CHANGED
|
@@ -156,7 +156,7 @@ module Robotstxt
|
|
|
156
156
|
@rules.last[2]<< r.gsub(/\*/,'.+') if r.length > 0
|
|
157
157
|
|
|
158
158
|
when /^\s*sitemap\s*:.+$/
|
|
159
|
-
@sitemaps<< r.split(':')[1].strip + r.split(':')[2].strip if r.length > 0
|
|
159
|
+
@sitemaps<< r.split(':')[1].strip + ((r.split(':')[2].nil?) ? '' : r.split(':')[2].strip) if r.length > 0
|
|
160
160
|
|
|
161
161
|
end
|
|
162
162
|
|
data/robotstxt.gemspec
CHANGED
|
@@ -2,11 +2,11 @@
|
|
|
2
2
|
|
|
3
3
|
Gem::Specification.new do |s|
|
|
4
4
|
s.name = %q{robotstxt}
|
|
5
|
-
s.version = "0.5.
|
|
5
|
+
s.version = "0.5.3"
|
|
6
6
|
|
|
7
7
|
s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
|
|
8
8
|
s.authors = ["Simone Rinzivillo"]
|
|
9
|
-
s.date = %q{
|
|
9
|
+
s.date = %q{2010-02-13}
|
|
10
10
|
s.description = %q{ Robotstxt Parser allows you to the check the accessibility of URLs and get other data. Full support for the robots.txt RFC, wildcards and Sitemap: rules.
|
|
11
11
|
}
|
|
12
12
|
s.email = %q{srinzivillo@gmail.com}
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: robotstxt
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.5.
|
|
4
|
+
version: 0.5.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Simone Rinzivillo
|
|
@@ -9,7 +9,7 @@ autorequire:
|
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
11
|
|
|
12
|
-
date:
|
|
12
|
+
date: 2010-02-13 00:00:00 +01:00
|
|
13
13
|
default_executable:
|
|
14
14
|
dependencies:
|
|
15
15
|
- !ruby/object:Gem::Dependency
|