web_rules 0.0.1 → 0.0.2
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/web_rules.rb +9 -2
- data/lib/web_rules/version.rb +1 -1
- metadata +2 -2
data/lib/web_rules.rb
CHANGED
@@ -1,6 +1,7 @@
|
|
1
1
|
require "web_rules/version"
|
2
2
|
require 'nokogiri'
|
3
3
|
require 'open-uri'
|
4
|
+
require 'timeout'
|
4
5
|
|
5
6
|
module WebRules
|
6
7
|
|
@@ -8,7 +9,11 @@ module WebRules
|
|
8
9
|
return if recurse <= 0
|
9
10
|
result = @objects[id]
|
10
11
|
begin
|
11
|
-
doc =
|
12
|
+
doc = ''
|
13
|
+
status = Timeout::timeout(4) do
|
14
|
+
doc = Nokogiri::HTML(open(url))
|
15
|
+
end
|
16
|
+
# puts status
|
12
17
|
rescue Exception => e
|
13
18
|
puts e,"----",url
|
14
19
|
return nil
|
@@ -23,6 +28,7 @@ module WebRules
|
|
23
28
|
next
|
24
29
|
end
|
25
30
|
result[r['href']] = url
|
31
|
+
print "."
|
26
32
|
a = r['href']
|
27
33
|
begin
|
28
34
|
a = URI::HTTP.build({:host => URI.parse(host).host, :path => r['href']}).to_s if uri.host.nil?
|
@@ -43,7 +49,8 @@ module WebRules
|
|
43
49
|
host = URI::HTTP.build({host: uri.host}).to_s
|
44
50
|
id = unique_id
|
45
51
|
@objects[id] = {}
|
46
|
-
recurse_select_refs(host, url,
|
52
|
+
recurse_select_refs(host, url, level, id)
|
53
|
+
puts "+"
|
47
54
|
# puts "-----------------------", @objects[id].length
|
48
55
|
@data_stack.push id
|
49
56
|
end
|
data/lib/web_rules/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: web_rules
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-11-
|
12
|
+
date: 2012-11-14 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
14
|
description: Hi level web access library got rules
|
15
15
|
email:
|