scrapers 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4807185dd0cee3d545e7db022cc5d310298e8792
-  data.tar.gz: d39450c7f4f6325eb73a864bdb476a9af3177d7a
+  metadata.gz: db591801f04aaf0af906b5b93790c8ee7521a6d1
+  data.tar.gz: a72274f8326f3f1ad4412b15dec1fd801d821bad
 SHA512:
-  metadata.gz: 1a32d5e6a3cad4644a5a4ee34e817d650aeff240152e60a875562fc465697221676598f67d6b13707201ac014d5634afce4c1177571d2fea802c74b8295bbed4
-  data.tar.gz: 67e51797361ad9c21dcc8d7c3200f3f3190ca98ce5402359f51aaefced4f41a34fadd8912e45480c49ce49e0baed2558570734413fa96e6f35f56f355011ed60
+  metadata.gz: 824c3b131c1bdcd1f4cfecba7b691eb1c07110075ca884452c2476614ec8d9466214c8c42e201e8516f04d67cdb96444840fbbe4015f4fdb5752501768d4f4c5
+  data.tar.gz: b7c9dcb97048074027e88d75f3fcedac78066b04a1cddf9b27dea075321523c31f4224842e14c770e37bf797c3064d3995321a4baa53b3e3574d64473611d100

data/.gitignore

@@ -16,3 +16,4 @@ test/tmp
 test/version_tmp
 tmp
 .rspec
+.tapas

data/lib/scrapers/rubytapas.rb

@@ -0,0 +1,65 @@
+require 'fileutils'
+require 'ostruct'
+
+module Scrapers
+  
+  module RubyTapas
+
+    module_function
+
+    # Save the post and attachments from an episode of RubyTapas
+    # in a directory determined from the episode title.
+    #
+    # Example:
+    #  episode url: "https://rubytapas.dpdcart.com/subscriber/post?id=443"
+    #  title: "177 Aliasing | RubyTapas"
+    #  subdirectory: /177-aliasing
+    #
+    # Parameters:
+    #
+    # * *url* - url of the episode to download
+    # * *user* - username used to log into dpdcart
+    # * *pw* - password used with username
+    # * *dest* - destination directory to put episode subdirectory
+    #
+    def scrape(url=nil, user=nil, pw=nil, dest=".")
+      raise "Must give user and password for RubyTapas downloads" if user.to_s.empty? or pw.to_s.empty?
+      dest = File.realdirpath(dest)
+      raise "Destination #{dest} must be a writeable directory" unless File.directory?(dest) and File.writable?(dest)
+
+      Mechanize.start do |m|
+
+        tapas = OpenStruct.new
+
+        # First time, we will get redirected to the login page
+        m.get url
+        m.current_page.form.field_with(:name => "username").value = user
+        m.current_page.form.field_with(:name => "password").value = pw
+        m.current_page.form.submit
+
+        # Second time, we should land on episode page
+        m.get url
+        raise "Not where I expected. #{m.current_page.uri} is not #{url}" unless m.current_page.uri != url
+
+        m.current_page.tap do |page|
+          tapas.title = page.title.strip
+          tapas.episode_dir = File.join(dest,tapas.title.split("|").first.strip.downcase.gsub(%r{\s+},'-'))
+          tapas.attachments = page.links_with(:href => %r{\bdownload\b})
+          FileUtils.mkdir(tapas.episode_dir)
+          Dir.chdir(tapas.episode_dir) do |dir|
+            tapas.attachments.each do |att|
+              puts "fetching #{att.text}"
+              file = att.click
+              puts "saving #{file.filename}"
+              file.save
+            end
+          end
+        end
+        
+        tapas
+        
+      end
+    end
+  end
+  
+end

data/lib/scrapers/version.rb

@@ -2,7 +2,7 @@ module Scrapers
   module Version
 
     MAJOR = 1
-    MINOR = 1
+    MINOR = 2
     BUILD = 0
 
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: scrapers
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Tamara Temple
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-15 00:00:00.000000000 Z
+date: 2014-02-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -145,6 +145,7 @@ files:
 - lib/scrapers/gocomics.rb
 - lib/scrapers/imgur.rb
 - lib/scrapers/nasa_apod.rb
+- lib/scrapers/rubytapas.rb
 - lib/scrapers/sinfest.rb
 - lib/scrapers/version.rb
 - lib/scrapers/xkcd.rb
@@ -202,3 +203,4 @@ test_files:
 - spec/scrapers/xkcd_spec.rb
 - spec/scrapers_spec.rb
 - spec/spec_helper.rb
+has_rdoc: