Merge pull request #1 from everypolitician-scrapers/initial-scraper

Initial scraper

.rubocop.yml

@@ -0,0 +1,9 @@
+AllCops:
+  Exclude:
+    - 'Vagrantfile'
+    - 'vendor/**/*'
+  TargetRubyVersion: 2.3
+
+inherit_from: 
+  - https://raw.githubusercontent.com/everypolitician/everypolitician-data/master/.rubocop_base.yml
+  - .rubocop_todo.yml

.travis.yml

@@ -0,0 +1,5 @@
+language: ruby
+rvm:
+  - 2.3.3
+sudo: false
+cache: bundler

Gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+ruby '2.3.3'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}.git" }
+
+gem 'pry'
+gem 'rake'
+gem 'rubocop'
+gem 'scraped', github: 'everypolitician/scraped'
+gem 'scraped_page_archive', github: 'everypolitician/scraped_page_archive'
+gem 'scraperwiki', github: 'openaustralia/scraperwiki-ruby',
+                   branch: 'morph_defaults'

Rakefile

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+require 'rubocop/rake_task'
+
+RuboCop::RakeTask.new
+
+task default: %w(rubocop)

scraper.rb

@@ -0,0 +1,20 @@
+#!/bin/env ruby
+# encoding: utf-8
+# frozen_string_literal: true
+
+require 'pry'
+require 'scraped_page_archive/open-uri'
+require 'scraped'
+
+class String
+  def tidy
+    gsub(/[[:space:]]+/, ' ').strip
+  end
+end
+
+def scrape_list(url)
+  puts "Opening #{url}"
+  Scraped::HTML.new(response: Scraped::Request.new(url: url).response)
+end
+
+scrape_list('http://www.palemene.ws/new/members-of-parliament/members-of-the-xvi-parliament/')