guardianscraper 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 7844bf4e98d141cf05ae449a8cf20dcaf99cadc9
+  data.tar.gz: 462c193afcfec2d3535bd585d4256f35f393982a
+SHA512:
+  metadata.gz: b5ae4e816de1b2efaea18456bf53d3d1587561d82bc086e31decfb8c0e88d9a9d96e3d8567bd886ae75301cb7e9505910163af3ce692ed64a1b58e0855736992
+  data.tar.gz: 78071d2df2b3fc6a42d36d6ceb064b7279c51b5d02ac16bdc1c5408218f514bbb126c96e31124c38fde9504600c9678a4b66d5ef0714ccc888808293dead1c99

data/lib/guardianscraper.rb

@@ -0,0 +1,36 @@
+require 'nokogiri'
+require 'open-uri'
+require 'json'
+
+# Scraper for the articles about the NSA docs in the Guardian
+class GuardianScraper
+  def initialize(url)
+    @url = url
+  end
+
+  # Download the article and save the text and other data
+  def getArticle
+    articlehash = Hash.new
+    html = Nokogiri::HTML(open(@url))
+
+    # Gets misc data on article
+    articlehash[:headline] = html.css('h1[itemprop="name headline  "]').text
+    articlehash[:description] = html.css('div[itemprop="description"]').text
+    articlehash[:date] = html.css('time[itemprop="datePublished"]').text
+    articlehash[:author] = html.css("a.contributor").text
+    articlehash[:published_by] = "The Guardian"                                                     
+    articlehash[:caption] = html.css("div.caption").text
+
+    # Gets list of documents linked to
+    articlehash[:documents] = Array.new
+    html.css('div[itemprop="description"]').css("a").each do |d|
+      articlehash[:documents].push(d["href"])
+    end
+    
+    # Gets text of article
+    articlehash[:text] = html.css("div#article-body-blocks").text
+    articlehash[:plaintext] = html.css("div#article-body-blocks").text
+
+    JSON.pretty_generate(articlehash)
+  end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: guardianscraper
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- M. C. McGrath
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-04-29 00:00:00.000000000 Z
+dependencies: []
+description: Scrapes Guardian articles.
+email: shidash@shidash.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/guardianscraper.rb
+homepage: https://github.com/Shidash/GuardianScraper
+licenses:
+- GPL
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Scrapes Guardian articles
+test_files: []
+has_rdoc: