From 4398b1212a7546163dd0dc1e97dadefdfc88e1f9 Mon Sep 17 00:00:00 2001 From: magnolia-fan Date: Tue, 15 Nov 2011 18:41:51 +0400 Subject: [PATCH] Parsing discogs better --- .vagrant | 1 + Gemfile.lock | 2 +- Vagrantfile | 86 ++++++++++++++++++++++++++++++++++++++ app/models/music/artist.rb | 9 ++++ lib/discogs.rb | 7 +++- 5 files changed, 102 insertions(+), 3 deletions(-) create mode 100644 .vagrant create mode 100644 Vagrantfile diff --git a/.vagrant b/.vagrant new file mode 100644 index 0000000..75f3828 --- /dev/null +++ b/.vagrant @@ -0,0 +1 @@ +{"active":{"default":"71a46e2b-83dd-40e6-8ff3-4df104a58955"}} \ No newline at end of file diff --git a/Gemfile.lock b/Gemfile.lock index 17b66ab..351a1f8 100644 --- a/Gemfile.lock +++ b/Gemfile.lock @@ -107,7 +107,7 @@ GEM sprockets (2.0.3) hike (~> 1.2) rack (~> 1.0) - tilt (!= 1.3.0, ~> 1.1) + tilt (~> 1.1, != 1.3.0) therubyracer (0.9.8) libv8 (~> 3.3.10) thor (0.14.6) diff --git a/Vagrantfile b/Vagrantfile new file mode 100644 index 0000000..5037fcb --- /dev/null +++ b/Vagrantfile @@ -0,0 +1,86 @@ +Vagrant::Config.run do |config| + # All Vagrant configuration is done here. The most common configuration + # options are documented and commented below. For a complete reference, + # please see the online documentation at vagrantup.com. + + # Every Vagrant virtual environment requires a box to build off of. + config.vm.box = "base" + + # The url from where the 'config.vm.box' box will be fetched if it + # doesn't already exist on the user's system. + # config.vm.box_url = "http://domain.com/path/to/above.box" + + # Boot with a GUI so you can see the screen. (Default is headless) + # config.vm.boot_mode = :gui + + # Assign this VM to a host only network IP, allowing you to access it + # via the IP. + # config.vm.network "33.33.33.10" + + # Forward a port from the guest to the host, which allows for outside + # computers to access the VM, whereas host only networking does not. + # config.vm.forward_port "http", 80, 8080 + + # Share an additional folder to the guest VM. The first argument is + # an identifier, the second is the path on the guest to mount the + # folder, and the third is the path on the host to the actual folder. + # config.vm.share_folder "v-data", "/vagrant_data", "../data" + + # Enable provisioning with Puppet stand alone. Puppet manifests + # are contained in a directory path relative to this Vagrantfile. + # You will need to create the manifests directory and a manifest in + # the file base.pp in the manifests_path directory. + # + # An example Puppet manifest to provision the message of the day: + # + # # group { "puppet": + # # ensure => "present", + # # } + # # + # # File { owner => 0, group => 0, mode => 0644 } + # # + # # file { '/etc/motd': + # # content => "Welcome to your Vagrant-built virtual machine! + # # Managed by Puppet.\n" + # # } + # + # config.vm.provision :puppet do |puppet| + # puppet.manifests_path = "manifests" + # puppet.manifest_file = "base.pp" + # end + + # Enable provisioning with chef solo, specifying a cookbooks path (relative + # to this Vagrantfile), and adding some recipes and/or roles. + # + # config.vm.provision :chef_solo do |chef| + # chef.cookbooks_path = "cookbooks" + # chef.add_recipe "mysql" + # chef.add_role "web" + # + # # You may also specify custom JSON attributes: + # chef.json = { :mysql_password => "foo" } + # end + + # Enable provisioning with chef server, specifying the chef server URL, + # and the path to the validation key (relative to this Vagrantfile). + # + # The Opscode Platform uses HTTPS. Substitute your organization for + # ORGNAME in the URL and validation key. + # + # If you have your own Chef Server, use the appropriate URL, which may be + # HTTP instead of HTTPS depending on your configuration. Also change the + # validation key to validation.pem. + # + # config.vm.provision :chef_client do |chef| + # chef.chef_server_url = "https://api.opscode.com/organizations/ORGNAME" + # chef.validation_key_path = "ORGNAME-validator.pem" + # end + # + # If you're using the Opscode platform, your validator client is + # ORGNAME-validator, replacing ORGNAME with your organization name. + # + # IF you have your own Chef Server, the default validation client name is + # chef-validator, unless you changed the configuration. + # + # chef.validation_client_name = "ORGNAME-validator" +end diff --git a/app/models/music/artist.rb b/app/models/music/artist.rb index 04ab964..08cdf1b 100644 --- a/app/models/music/artist.rb +++ b/app/models/music/artist.rb @@ -9,6 +9,15 @@ class Artist < ActiveRecord::Base def status_str %w(loading ok fail)[self.status] end + + def load_again! + albums.each(&:destroy) + artist_links.each(&:destroy) + artist_aliases.each(&:destroy) + self.status = 0 + save! + Delayed::Job.enqueue(LoadArtistJob.new(name)) + end private diff --git a/lib/discogs.rb b/lib/discogs.rb index f0dc6ab..a887f79 100644 --- a/lib/discogs.rb +++ b/lib/discogs.rb @@ -144,7 +144,10 @@ class Discogs if split == 2 break end - if _.attr('class').match(/^main.*/) and _.css('td')[3].text.scan(/\d/).join('') != '' and _.css('a.mr_toggler').length == 1 + if _.attr('class').match(/^main.*/) and _.css('td')[3].text.scan(/\d/).join('') != '' and ( + _.css('a.mr_toggler').length == 1 or + _.css('td')[1].text.match(/\(.*?Album.*?\)/).present? + ) albums << { :uri => (_.attr('class').match(/master/) ? 'master/' : 'release/')+_.attr('id')[1,100], :title => _.css('h4 > a').first.text, @@ -152,7 +155,7 @@ class Discogs } end end - albums + ap albums end def self.search_for_artist name