apollo-crawler 0.0.34 → 0.0.35
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.
@@ -0,0 +1,40 @@
|
|
1
|
+
require 'iconv'
|
2
|
+
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'plugin')
|
4
|
+
|
5
|
+
module Apollo
|
6
|
+
module Crawler
|
7
|
+
module Plugins
|
8
|
+
# PARAMATRIZE: Plugin class name
|
9
|
+
class Xkcd < Plugin
|
10
|
+
@@URL = "http://xkcd.com/"
|
11
|
+
|
12
|
+
@@MATCHER_ITEM = "//div[@id = 'comic']/img"
|
13
|
+
|
14
|
+
def name()
|
15
|
+
return "Xkcd"
|
16
|
+
end
|
17
|
+
|
18
|
+
def run()
|
19
|
+
ic = Iconv.new("UTF-8//IGNORE", "UTF-8")
|
20
|
+
|
21
|
+
# TODO: Encapsulate and make more robust => invalid hostname, timeouts and so
|
22
|
+
doc = Nokogiri::HTML(ic.iconv(open(@@URL).read))
|
23
|
+
|
24
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |node|
|
25
|
+
{
|
26
|
+
:text => node['title'],
|
27
|
+
:link => URI.join(@@URL, node['src'])
|
28
|
+
}
|
29
|
+
}
|
30
|
+
|
31
|
+
return {
|
32
|
+
:plugin => self.class.name,
|
33
|
+
:title => doc.title,
|
34
|
+
:res => res
|
35
|
+
}
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end # Plugins
|
39
|
+
end # Crawler
|
40
|
+
end # Apollo
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: apollo-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.35
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -59,6 +59,22 @@ dependencies:
|
|
59
59
|
- - ! '>='
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: mime-types
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
62
78
|
- !ruby/object:Gem::Dependency
|
63
79
|
name: nokogiri
|
64
80
|
requirement: !ruby/object:Gem::Requirement
|
@@ -75,6 +91,38 @@ dependencies:
|
|
75
91
|
- - ! '>='
|
76
92
|
- !ruby/object:Gem::Version
|
77
93
|
version: '0'
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: openurl
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
type: :runtime
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
- !ruby/object:Gem::Dependency
|
111
|
+
name: parallel
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
none: false
|
122
|
+
requirements:
|
123
|
+
- - ! '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
78
126
|
- !ruby/object:Gem::Dependency
|
79
127
|
name: thor
|
80
128
|
requirement: !ruby/object:Gem::Requirement
|
@@ -101,6 +149,7 @@ files:
|
|
101
149
|
- ./lib/apollo_crawler/version.rb
|
102
150
|
- ./lib/apollo_crawler/crawler.rb
|
103
151
|
- ./lib/apollo_crawler/plugin_template.rb
|
152
|
+
- ./lib/apollo_crawler/plugins/xkcd_com/xkcd.rb
|
104
153
|
- ./lib/apollo_crawler/plugins/slashdot_org/slashdot.rb
|
105
154
|
- ./lib/apollo_crawler/plugins/firmy_cz/firmy.rb
|
106
155
|
- ./lib/apollo_crawler/plugins/alexa_com/alexa.rb
|