Gardeners World 'What to do now' checklist scraper

.gitignore

@@ -0,0 +1,2 @@
+data.sqlite
+.cache

Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+gem 'pry'
+gem 'scraperwiki', git: 'https://github.com/openaustralia/scraperwiki-ruby.git', branch: 'morph_defaults'
+gem 'nokogiri'
+gem 'open-uri-cached', require: 'open-uri/cached'

Gemfile.lock

@@ -0,0 +1,39 @@
+GIT
+  remote: https://github.com/openaustralia/scraperwiki-ruby.git
+  revision: fc50176812505e463077d5c673d504a6a234aa78
+  branch: morph_defaults
+  specs:
+    scraperwiki (3.0.1)
+      httpclient
+      sqlite_magic
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    coderay (1.1.1)
+    httpclient (2.7.1)
+    method_source (0.8.2)
+    mini_portile2 (2.0.0)
+    nokogiri (1.6.7.2)
+      mini_portile2 (~> 2.0.0.rc2)
+    open-uri-cached (0.0.5)
+    pry (0.10.3)
+      coderay (~> 1.1.0)
+      method_source (~> 0.8.1)
+      slop (~> 3.4)
+    slop (3.6.0)
+    sqlite3 (1.3.11)
+    sqlite_magic (0.0.6)
+      sqlite3
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  nokogiri
+  open-uri-cached
+  pry
+  scraperwiki!
+
+BUNDLED WITH
+   1.11.2

scraper.rb

@@ -0,0 +1,22 @@
+require 'bundler'
+Bundler.require
+OpenURI::Cache.cache_path = '.cache'
+
+require 'open-uri'
+
+sections = %w(flowers-checklist fruit-veg-checklist greenhouse-checklist around-garden-checklist)
+1.upto(52) do |week_number|
+  sections.each do |section|
+    url = "http://www.gardenersworld.com/what-to-do-now/week#{week_number}/#{section}/?print=true"
+    warn "Fetching: #{url}"
+    page = Nokogiri::HTML(open(url))
+    page.css('.checklist ul:first li').each do |job|
+      data = {
+        week: week_number,
+        section: section,
+        job: job.text
+      }
+      ScraperWiki.save_sqlite([:week, :section, :job], data)
+    end
+  end
+end