wlsearchscraper 0.0.1

data/lib/wlsearchscraper.rb

@@ -0,0 +1,25 @@
+require 'nokogiri'
+require 'open-uri'
+
+class WLSearchScraper
+  def initialize(searchterms)
+    @searchterms = searchterms
+    @resultlist = Array.new
+  end
+  
+  # Returns array of document IDs matching search terms
+  def scrape
+    @searchterms.gsub!(" ", "+")
+    url = "https://search.wikileaks.org/advanced?q=" + @searchterms + "&exclude_words=&words_title_only=&words_content_only=&publication_type[]=3"
+    html = Nokogiri::HTML(open(url))
+
+    html.css("h4").each do |h|
+      href = h.css("a")[0]["href"]
+      split = href.split("/")
+      cable = split[split.length-1].split("_a.html")
+      @resultlist.push(cable[0])
+    end
+    
+    return @resultlist
+  end
+end

metadata

@@ -0,0 +1,48 @@
+--- !ruby/object:Gem::Specification
+name: wlsearchscraper
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- M. C. McGrath
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-03-27 00:00:00.000000000 Z
+dependencies: []
+description: Gets a list of documents from the WikiLeaks search that match certain
+  terms.
+email: shidash@shidash.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/wlsearchscraper.rb
+homepage: https://github.com/Shidash/wlsearchscraper
+licenses:
+- GPL
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: Gets list of documents from WikiLeaks search.
+test_files: []
+has_rdoc: