1
0
Fork 0

Parsing discogs better

This commit is contained in:
magnolia-fan 2011-11-15 18:41:51 +04:00
parent 1a5e0cb819
commit 4398b1212a
5 changed files with 102 additions and 3 deletions

1
.vagrant Normal file
View File

@ -0,0 +1 @@
{"active":{"default":"71a46e2b-83dd-40e6-8ff3-4df104a58955"}}

View File

@ -107,7 +107,7 @@ GEM
sprockets (2.0.3) sprockets (2.0.3)
hike (~> 1.2) hike (~> 1.2)
rack (~> 1.0) rack (~> 1.0)
tilt (!= 1.3.0, ~> 1.1) tilt (~> 1.1, != 1.3.0)
therubyracer (0.9.8) therubyracer (0.9.8)
libv8 (~> 3.3.10) libv8 (~> 3.3.10)
thor (0.14.6) thor (0.14.6)

86
Vagrantfile vendored Normal file
View File

@ -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

View File

@ -9,6 +9,15 @@ class Artist < ActiveRecord::Base
def status_str def status_str
%w(loading ok fail)[self.status] %w(loading ok fail)[self.status]
end 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 private

View File

@ -144,7 +144,10 @@ class Discogs
if split == 2 if split == 2
break break
end 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 << { albums << {
:uri => (_.attr('class').match(/master/) ? 'master/' : 'release/')+_.attr('id')[1,100], :uri => (_.attr('class').match(/master/) ? 'master/' : 'release/')+_.attr('id')[1,100],
:title => _.css('h4 > a').first.text, :title => _.css('h4 > a').first.text,
@ -152,7 +155,7 @@ class Discogs
} }
end end
end end
albums ap albums
end end
def self.search_for_artist name def self.search_for_artist name