colinramsay-robotstxt 1.0 → 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/README +5 -1
- data/lib/robotstxtparser.rb +6 -3
- metadata +2 -2
data/README
CHANGED
|
@@ -11,7 +11,11 @@ Disallow: /logs
|
|
|
11
11
|
User-agent: Google
|
|
12
12
|
Disallow: /admin
|
|
13
13
|
|
|
14
|
+
Use it like this:
|
|
15
|
+
|
|
16
|
+
require 'robotstxtparser'
|
|
17
|
+
|
|
14
18
|
# Also accepts a local file
|
|
15
|
-
rp =
|
|
19
|
+
rp = RobotsTxtParser.new("http://something.com/robots.txt")
|
|
16
20
|
|
|
17
21
|
rp.user_agents('Google') # returns ["/logs", "/admin"]
|
data/lib/robotstxtparser.rb
CHANGED
|
@@ -8,13 +8,16 @@ class RobotsTxtParser
|
|
|
8
8
|
if path.include?("://")
|
|
9
9
|
raw_data = open(path)
|
|
10
10
|
else
|
|
11
|
-
|
|
11
|
+
begin
|
|
12
|
+
raw_data = File.open(path)
|
|
13
|
+
rescue
|
|
14
|
+
end
|
|
12
15
|
end
|
|
13
16
|
|
|
14
|
-
return unless raw_data
|
|
15
|
-
|
|
16
17
|
@user_agents = Hash.new
|
|
17
18
|
|
|
19
|
+
return unless raw_data
|
|
20
|
+
|
|
18
21
|
parse(raw_data)
|
|
19
22
|
end
|
|
20
23
|
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: colinramsay-robotstxt
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version:
|
|
4
|
+
version: 1.0.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Colin Ramsay
|
|
@@ -9,7 +9,7 @@ autorequire:
|
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
11
|
|
|
12
|
-
date: 2009-06-
|
|
12
|
+
date: 2009-06-30 00:00:00 -07:00
|
|
13
13
|
default_executable:
|
|
14
14
|
dependencies: []
|
|
15
15
|
|