apollo-crawler 0.0.43 → 0.0.44
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 +1,30 @@
|
|
|
1
|
+
require 'iconv'
|
|
2
|
+
|
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'plugin')
|
|
4
|
+
|
|
5
|
+
module Apollo
|
|
6
|
+
module Crawler
|
|
7
|
+
module Plugins
|
|
8
|
+
class StackOverflow < Plugin
|
|
9
|
+
@@MATCHER_ITEM = "//div[@class = 'summary']/h3/a"
|
|
10
|
+
|
|
11
|
+
def name
|
|
12
|
+
return "StackOverflow"
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
def url()
|
|
16
|
+
return "http://stackoverflow.com/"
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
def extract_data(doc)
|
|
20
|
+
res = doc.xpath(@@MATCHER_ITEM).map { |i|
|
|
21
|
+
{
|
|
22
|
+
:text => i.text,
|
|
23
|
+
:link => URI.join(self.url, i['href'])
|
|
24
|
+
}
|
|
25
|
+
}
|
|
26
|
+
end
|
|
27
|
+
end
|
|
28
|
+
end # Plugins
|
|
29
|
+
end # Crawler
|
|
30
|
+
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: 0.0.44
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -233,6 +233,7 @@ files:
|
|
|
233
233
|
- ./lib/apollo_crawler/crawler.rb
|
|
234
234
|
- ./lib/apollo_crawler/formatter.rb
|
|
235
235
|
- ./lib/apollo_crawler/plugin_template.rb
|
|
236
|
+
- ./lib/apollo_crawler/plugins/stackoverflow_com/stackoverflow.rb
|
|
236
237
|
- ./lib/apollo_crawler/plugins/xkcd_com/xkcd.rb
|
|
237
238
|
- ./lib/apollo_crawler/plugins/slashdot_org/slashdot.rb
|
|
238
239
|
- ./lib/apollo_crawler/plugins/firmy_cz/firmy.rb
|