wlsearchscraper 0.0.1
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/lib/wlsearchscraper.rb +25 -0
- metadata +48 -0
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
require 'nokogiri'
|
|
2
|
+
require 'open-uri'
|
|
3
|
+
|
|
4
|
+
class WLSearchScraper
|
|
5
|
+
def initialize(searchterms)
|
|
6
|
+
@searchterms = searchterms
|
|
7
|
+
@resultlist = Array.new
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
# Returns array of document IDs matching search terms
|
|
11
|
+
def scrape
|
|
12
|
+
@searchterms.gsub!(" ", "+")
|
|
13
|
+
url = "https://search.wikileaks.org/advanced?q=" + @searchterms + "&exclude_words=&words_title_only=&words_content_only=&publication_type[]=3"
|
|
14
|
+
html = Nokogiri::HTML(open(url))
|
|
15
|
+
|
|
16
|
+
html.css("h4").each do |h|
|
|
17
|
+
href = h.css("a")[0]["href"]
|
|
18
|
+
split = href.split("/")
|
|
19
|
+
cable = split[split.length-1].split("_a.html")
|
|
20
|
+
@resultlist.push(cable[0])
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
return @resultlist
|
|
24
|
+
end
|
|
25
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: wlsearchscraper
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- M. C. McGrath
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2014-03-27 00:00:00.000000000 Z
|
|
13
|
+
dependencies: []
|
|
14
|
+
description: Gets a list of documents from the WikiLeaks search that match certain
|
|
15
|
+
terms.
|
|
16
|
+
email: shidash@shidash.com
|
|
17
|
+
executables: []
|
|
18
|
+
extensions: []
|
|
19
|
+
extra_rdoc_files: []
|
|
20
|
+
files:
|
|
21
|
+
- lib/wlsearchscraper.rb
|
|
22
|
+
homepage: https://github.com/Shidash/wlsearchscraper
|
|
23
|
+
licenses:
|
|
24
|
+
- GPL
|
|
25
|
+
post_install_message:
|
|
26
|
+
rdoc_options: []
|
|
27
|
+
require_paths:
|
|
28
|
+
- lib
|
|
29
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
30
|
+
none: false
|
|
31
|
+
requirements:
|
|
32
|
+
- - ! '>='
|
|
33
|
+
- !ruby/object:Gem::Version
|
|
34
|
+
version: '0'
|
|
35
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
36
|
+
none: false
|
|
37
|
+
requirements:
|
|
38
|
+
- - ! '>='
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
requirements: []
|
|
42
|
+
rubyforge_project:
|
|
43
|
+
rubygems_version: 1.8.23
|
|
44
|
+
signing_key:
|
|
45
|
+
specification_version: 3
|
|
46
|
+
summary: Gets list of documents from WikiLeaks search.
|
|
47
|
+
test_files: []
|
|
48
|
+
has_rdoc:
|