yandex_cleanweb 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- data/.travis.yml +8 -0
- data/README.md +20 -0
- data/Rakefile +12 -0
- data/lib/yandex_cleanweb/version.rb +1 -1
- data/lib/yandex_cleanweb.rb +19 -36
- data/test/test_helper.rb +7 -0
- data/test/yandex_cleanweb_test.rb +48 -0
- data/yandex_cleanweb.gemspec +3 -0
- metadata +40 -3
data/.travis.yml
ADDED
data/README.md
CHANGED
@@ -1,7 +1,11 @@
|
|
1
1
|
# Yandex Cleanweb
|
2
2
|
|
3
|
+
[![Build Status](https://travis-ci.org/evrone/yandex-cleanweb.png?branch=master)](https://travis-ci.org/evrone/yandex-cleanweb)
|
4
|
+
|
3
5
|
Ruby wrapper for [Yandex Cleanweb](http://api.yandex.ru/cleanweb/) spam detector.
|
4
6
|
|
7
|
+
Unfortunatelly, this gem *is not capable with MRI 1.8.7* because of MRI 1.8.7 doesn't have `URI.encode_www_form` method.
|
8
|
+
|
5
9
|
## Installation
|
6
10
|
|
7
11
|
Add this line to your application's Gemfile:
|
@@ -32,6 +36,22 @@ YandexCleanweb.spam?(body_html: "some spam <a href='http://spam.com'>spam link</
|
|
32
36
|
=> { id: "request id", links: [ ['http://spam.com', true] ] }
|
33
37
|
```
|
34
38
|
|
39
|
+
More complex example:
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
|
43
|
+
user_input = "download free porn <a>...</a>"
|
44
|
+
if spam_check = YandexCleanweb.spam?(user_input, ip: current_user.ip)
|
45
|
+
captcha = YandexCleanweb.get_captcha(spam_check[:id])
|
46
|
+
|
47
|
+
# now you can show captcha[:url] to user
|
48
|
+
# but remember to write captcha[:captcha] to session
|
49
|
+
|
50
|
+
# to check is captcha enterred by user is valid:
|
51
|
+
captcha_valid = YandexCleanweb.valid_captcha?(result[:id], captcha[:captcha], user_captcha)
|
52
|
+
end
|
53
|
+
```
|
54
|
+
|
35
55
|
If you use Yandex Cleanweb in Rails app, we recommend to set up the api key in `config/initializers/yandex_cleanweb.rb`
|
36
56
|
|
37
57
|
## Contributing
|
data/Rakefile
CHANGED
data/lib/yandex_cleanweb.rb
CHANGED
@@ -17,15 +17,17 @@ module YandexCleanweb
|
|
17
17
|
request_id_tag = doc.xpath('//check-spam-result/id')
|
18
18
|
spam_flag_tag = doc.xpath('//check-spam-result/text')
|
19
19
|
|
20
|
-
request_id = request_id_tag[0]
|
20
|
+
request_id = request_id_tag[0].content
|
21
21
|
spam_flag = spam_flag_tag[0].attributes["spam-flag"].content
|
22
22
|
|
23
23
|
if spam_flag == 'yes'
|
24
|
-
links = doc.xpath('//check-spam-result/links').
|
25
|
-
[attributes["url"], attributes["spam_flag"] == 'yes']
|
26
|
-
}
|
24
|
+
links = doc.xpath('//check-spam-result/links')[0].children
|
27
25
|
|
28
|
-
|
26
|
+
links.map do |el|
|
27
|
+
[el.attributes["url"], el.attributes["spam_flag"] == 'yes']
|
28
|
+
end
|
29
|
+
|
30
|
+
{ :id => request_id, :links => links }
|
29
31
|
else
|
30
32
|
false
|
31
33
|
end
|
@@ -38,10 +40,7 @@ module YandexCleanweb
|
|
38
40
|
url = doc.xpath('//get-captcha-result/url').text
|
39
41
|
captcha_id = doc.xpath('//get-captcha-result/captcha').text
|
40
42
|
|
41
|
-
{
|
42
|
-
url: url,
|
43
|
-
captcha: captcha_id
|
44
|
-
}
|
43
|
+
{ :url => url, :captcha => captcha_id }
|
45
44
|
end
|
46
45
|
|
47
46
|
def valid_captcha?(request_id, captcha_id, value)
|
@@ -55,10 +54,10 @@ module YandexCleanweb
|
|
55
54
|
def api_check_captcha(request_id, captcha_id, value)
|
56
55
|
check_captcha_url = "#{API_URL}/check-captcha"
|
57
56
|
params = {
|
58
|
-
key
|
59
|
-
id
|
60
|
-
captcha
|
61
|
-
value
|
57
|
+
:key => api_key,
|
58
|
+
:id => request_id,
|
59
|
+
:captcha => captcha_id,
|
60
|
+
:value => value
|
62
61
|
}
|
63
62
|
|
64
63
|
uri = URI.parse(check_captcha_url)
|
@@ -69,7 +68,7 @@ module YandexCleanweb
|
|
69
68
|
|
70
69
|
def api_get_captcha(request_id)
|
71
70
|
get_captcha_url = "#{API_URL}/get-captcha"
|
72
|
-
params = {key
|
71
|
+
params = { :key => api_key, :id => request_id }
|
73
72
|
|
74
73
|
uri = URI.parse(get_captcha_url)
|
75
74
|
uri.query = URI.encode_www_form(params)
|
@@ -77,30 +76,14 @@ module YandexCleanweb
|
|
77
76
|
Net::HTTP.get(uri)
|
78
77
|
end
|
79
78
|
|
80
|
-
def api_check_spam(
|
81
|
-
cleanweb_options = {}
|
82
|
-
cleanweb_options["key"] = api_key
|
79
|
+
def api_check_spam(options)
|
80
|
+
cleanweb_options = { :key => api_key }
|
83
81
|
|
84
|
-
if options[0]
|
85
|
-
cleanweb_options[
|
82
|
+
if options[0].is_a?(String) # quick check
|
83
|
+
cleanweb_options[:body_plain] = options[0]
|
86
84
|
else
|
87
|
-
options = options[0]
|
88
|
-
|
89
|
-
cleanweb_options.merge!({
|
90
|
-
"body-plain" => options[:body_plain],
|
91
|
-
"body-html" => options[:body_html],
|
92
|
-
"body-bbcode" => options[:body_bbcode],
|
93
|
-
|
94
|
-
"subject-html" => options[:subject_html],
|
95
|
-
"subject-plain" => options[:subject_plain],
|
96
|
-
"subject-bbcode" => options[:subject_bbcode],
|
97
|
-
|
98
|
-
"ip" => options[:ip],
|
99
|
-
"email" => options[:email],
|
100
|
-
"name" => options[:name],
|
101
|
-
"login" => options[:login],
|
102
|
-
"realname" => options[:realname]
|
103
|
-
})
|
85
|
+
options = options[0]
|
86
|
+
cleanweb_options.merge!(Hash[options.map{ |k,v| [k.to_s.gsub("_","-"), v] }])
|
104
87
|
end
|
105
88
|
|
106
89
|
check_spam_url = "#{API_URL}/check-spam"
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require "test_helper"
|
3
|
+
|
4
|
+
describe YandexCleanweb do
|
5
|
+
before do
|
6
|
+
YandexCleanweb.api_key = "cw.1.1.20121227T080449Z.51de1ee126e5ced6.f4f417fb55727520d7e39b00cf5393d4b1ca5e78"
|
7
|
+
end
|
8
|
+
|
9
|
+
describe "#spam?" do
|
10
|
+
|
11
|
+
describe "simple check" do
|
12
|
+
it "works" do
|
13
|
+
YandexCleanweb.spam?("фраза").must_equal false
|
14
|
+
YandexCleanweb.spam?("недорого увеличение пениса проститутки").must_equal false
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
describe "advanced mode" do
|
19
|
+
it "workd" do
|
20
|
+
YandexCleanweb.spam?(:body_plain => "my text", :ip => "80.80.40.3").must_equal false
|
21
|
+
end
|
22
|
+
|
23
|
+
it "for some html" do
|
24
|
+
result = YandexCleanweb.spam?(:body_html => "some spam <a href='http://spam.com'>spam link</a>")
|
25
|
+
|
26
|
+
result[:id].wont_be_empty
|
27
|
+
result[:links].must_be_empty
|
28
|
+
end
|
29
|
+
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
33
|
+
|
34
|
+
describe "#get_captcha + #valid_captcha?" do
|
35
|
+
|
36
|
+
it "works for not valid captchas" do
|
37
|
+
result = YandexCleanweb.spam?(:body_html => "some spam <a href='http://spam.com'>spam link</a>")
|
38
|
+
captcha = YandexCleanweb.get_captcha(result[:id])
|
39
|
+
|
40
|
+
captcha[:url].wont_be_empty
|
41
|
+
captcha[:captcha].wont_be_empty
|
42
|
+
|
43
|
+
valid = YandexCleanweb.valid_captcha?(result[:id], captcha[:captcha], "1234")
|
44
|
+
valid.must_equal false
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
end
|
data/yandex_cleanweb.gemspec
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: yandex_cleanweb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
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: 2013-
|
12
|
+
date: 2013-03-30 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: nokogiri
|
@@ -27,6 +27,38 @@ dependencies:
|
|
27
27
|
- - ! '>='
|
28
28
|
- !ruby/object:Gem::Version
|
29
29
|
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: minitest
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '3.0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '3.0'
|
30
62
|
description: Ruby wrapper for Yandex.Cleanweb
|
31
63
|
email:
|
32
64
|
- shatrov@me.com
|
@@ -35,12 +67,15 @@ extensions: []
|
|
35
67
|
extra_rdoc_files: []
|
36
68
|
files:
|
37
69
|
- .gitignore
|
70
|
+
- .travis.yml
|
38
71
|
- Gemfile
|
39
72
|
- LICENSE.txt
|
40
73
|
- README.md
|
41
74
|
- Rakefile
|
42
75
|
- lib/yandex_cleanweb.rb
|
43
76
|
- lib/yandex_cleanweb/version.rb
|
77
|
+
- test/test_helper.rb
|
78
|
+
- test/yandex_cleanweb_test.rb
|
44
79
|
- yandex_cleanweb.gemspec
|
45
80
|
homepage: ''
|
46
81
|
licenses: []
|
@@ -66,4 +101,6 @@ rubygems_version: 1.8.23
|
|
66
101
|
signing_key:
|
67
102
|
specification_version: 3
|
68
103
|
summary: Ruby wrapper for Yandex.Cleanweb spam detector
|
69
|
-
test_files:
|
104
|
+
test_files:
|
105
|
+
- test/test_helper.rb
|
106
|
+
- test/yandex_cleanweb_test.rb
|