elvallenato 0.0.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.bundle/config +1 -0
- data/.document +5 -0
- data/.gitignore +21 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +57 -0
- data/Guardfile +30 -0
- data/LICENSE +20 -0
- data/README.rdoc +35 -0
- data/Rakefile +2 -0
- data/VERSION +1 -0
- data/autotest/discover.rb +9 -0
- data/elvallenato.gemspec +29 -0
- data/lib/elvallenato/letra.rb +30 -0
- data/lib/elvallenato/search.rb +65 -0
- data/lib/elvallenato/version.rb +3 -0
- data/lib/elvallenato.rb +12 -0
- data/spec/elvallenato_spec.rb +5 -0
- data/spec/fixtures/diomedes_search.htm +660 -0
- data/spec/fixtures/siete_palabras.htm +852 -0
- data/spec/letra_spec.rb +29 -0
- data/spec/search_spec.rb +55 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +7 -0
- metadata +185 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: face9e2c5e1d24fadb250ffe5aca8050c25e787c
|
4
|
+
data.tar.gz: c8d9fd37c89086591c64cb7378fe1fdfd910d1e1
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e7aa19f89a71036673df7711262c9376c85cef38429ae25e67f5e41df06de6182645d084ad94fb5671c1e7bf366ad6d66ac10995e5f31e98bd13a29ad1a5367e
|
7
|
+
data.tar.gz: 2a3e3a81c206e6227998bafea7eeb4c23e8a922bc5fb05ef178831c1e3a50acd58f2a8352ab0bffa91e70cbded4b643b34b42cd38797524490d87cf355d58e77
|
data/.bundle/config
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--- {}
|
data/.document
ADDED
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
elvallenato (0.0.5)
|
5
|
+
RedCloth
|
6
|
+
nokogiri
|
7
|
+
|
8
|
+
GEM
|
9
|
+
remote: http://rubygems.org/
|
10
|
+
specs:
|
11
|
+
RedCloth (4.2.9)
|
12
|
+
awesome_print (1.1.0)
|
13
|
+
coderay (1.1.0)
|
14
|
+
diff-lcs (1.2.5)
|
15
|
+
formatador (0.2.4)
|
16
|
+
guard (1.7.0)
|
17
|
+
formatador (>= 0.2.4)
|
18
|
+
listen (>= 0.6.0)
|
19
|
+
lumberjack (>= 1.0.2)
|
20
|
+
pry (>= 0.9.10)
|
21
|
+
thor (>= 0.14.6)
|
22
|
+
guard-bundler (1.0.0)
|
23
|
+
bundler (~> 1.0)
|
24
|
+
guard (~> 1.1)
|
25
|
+
guard-rspec (1.2.1)
|
26
|
+
guard (>= 1.1)
|
27
|
+
listen (0.7.3)
|
28
|
+
lumberjack (1.0.5)
|
29
|
+
method_source (0.8.2)
|
30
|
+
nokogiri (1.5.5)
|
31
|
+
pry (0.9.12.6)
|
32
|
+
coderay (~> 1.0)
|
33
|
+
method_source (~> 0.8)
|
34
|
+
slop (~> 3.4)
|
35
|
+
rb-fsevent (0.9.4)
|
36
|
+
rspec (2.14.1)
|
37
|
+
rspec-core (~> 2.14.0)
|
38
|
+
rspec-expectations (~> 2.14.0)
|
39
|
+
rspec-mocks (~> 2.14.0)
|
40
|
+
rspec-core (2.14.8)
|
41
|
+
rspec-expectations (2.14.5)
|
42
|
+
diff-lcs (>= 1.1.3, < 2.0)
|
43
|
+
rspec-mocks (2.14.6)
|
44
|
+
slop (3.5.0)
|
45
|
+
thor (0.19.1)
|
46
|
+
|
47
|
+
PLATFORMS
|
48
|
+
ruby
|
49
|
+
|
50
|
+
DEPENDENCIES
|
51
|
+
awesome_print
|
52
|
+
elvallenato!
|
53
|
+
guard
|
54
|
+
guard-bundler
|
55
|
+
guard-rspec
|
56
|
+
rb-fsevent
|
57
|
+
rspec
|
data/Guardfile
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# A sample Guardfile
|
2
|
+
# More info at https://github.com/guard/guard#readme
|
3
|
+
|
4
|
+
guard 'bundler' do
|
5
|
+
watch('Gemfile')
|
6
|
+
# Uncomment next line if Gemfile contain `gemspec' command
|
7
|
+
# watch(/^.+\.gemspec/)
|
8
|
+
end
|
9
|
+
|
10
|
+
guard 'rspec', :version => 2 do
|
11
|
+
watch(%r{^spec/.+_spec\.rb$})
|
12
|
+
watch(%r{^lib/(.+)\.rb$}) { |m| "spec/lib/#{m[1]}_spec.rb" }
|
13
|
+
watch('spec/spec_helper.rb') { "spec" }
|
14
|
+
|
15
|
+
# Rails example
|
16
|
+
watch(%r{^app/(.+)\.rb$}) { |m| "spec/#{m[1]}_spec.rb" }
|
17
|
+
watch(%r{^app/(.*)(\.erb|\.haml)$}) { |m| "spec/#{m[1]}#{m[2]}_spec.rb" }
|
18
|
+
watch(%r{^app/controllers/(.+)_(controller)\.rb$}) { |m| ["spec/routing/#{m[1]}_routing_spec.rb", "spec/#{m[2]}s/#{m[1]}_#{m[2]}_spec.rb", "spec/acceptance/#{m[1]}_spec.rb"] }
|
19
|
+
watch(%r{^spec/support/(.+)\.rb$}) { "spec" }
|
20
|
+
watch('config/routes.rb') { "spec/routing" }
|
21
|
+
watch('app/controllers/application_controller.rb') { "spec/controllers" }
|
22
|
+
|
23
|
+
# Capybara request specs
|
24
|
+
watch(%r{^app/views/(.+)/.*\.(erb|haml)$}) { |m| "spec/requests/#{m[1]}_spec.rb" }
|
25
|
+
|
26
|
+
# Turnip features and steps
|
27
|
+
watch(%r{^spec/acceptance/(.+)\.feature$})
|
28
|
+
watch(%r{^spec/acceptance/steps/(.+)_steps\.rb$}) { |m| Dir[File.join("**/#{m[1]}.feature")][0] || 'spec/acceptance' }
|
29
|
+
end
|
30
|
+
|
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 John Maya
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
= elvallenato
|
2
|
+
|
3
|
+
This application is designed to scrap data from el vallenato.com
|
4
|
+
|
5
|
+
= Examples
|
6
|
+
|
7
|
+
require 'rubygems'
|
8
|
+
require 'elvallenato'
|
9
|
+
#Optional if you want to import the namespace
|
10
|
+
include ElVallenato
|
11
|
+
s = Search.new('canta', "Jorge")
|
12
|
+
s.fetch_content
|
13
|
+
letras = s.collect_lirics
|
14
|
+
puts letras[0].title
|
15
|
+
puts letras[0].body
|
16
|
+
puts letras[0].artist
|
17
|
+
puts letras[0].composer
|
18
|
+
|
19
|
+
#if you want to go to the next page fetch the contents again
|
20
|
+
s.fetch_content
|
21
|
+
|
22
|
+
|
23
|
+
== Note on Patches/Pull Requests
|
24
|
+
|
25
|
+
* Fork the project.
|
26
|
+
* Make your feature addition or bug fix.
|
27
|
+
* Add tests for it. This is important so I don't break it in a
|
28
|
+
future version unintentionally.
|
29
|
+
* Commit, do not mess with rakefile, version, or history.
|
30
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
31
|
+
* Send me a pull request. Bonus points for topic branches.
|
32
|
+
|
33
|
+
== Copyright
|
34
|
+
|
35
|
+
Copyright (c) 2009 John Maya. See LICENSE for details.
|
data/Rakefile
ADDED
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.2
|
data/elvallenato.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "elvallenato/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "elvallenato"
|
7
|
+
s.version = Elvallenato::VERSION
|
8
|
+
s.platform = Gem::Platform::RUBY
|
9
|
+
s.authors = ["John Maya"]
|
10
|
+
s.email = ["jcmaya@hotmail.com"]
|
11
|
+
s.homepage = ""
|
12
|
+
s.summary = %q{This gem will interface with http://www.elvallenato.com}
|
13
|
+
s.description = %q{This gem will interface with http://www.elvallenato.com}
|
14
|
+
|
15
|
+
s.rubyforge_project = "elvallenato"
|
16
|
+
|
17
|
+
s.files = `git ls-files`.split("\n")
|
18
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
19
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
20
|
+
s.require_paths = ["lib"]
|
21
|
+
s.add_development_dependency('rspec')
|
22
|
+
s.add_development_dependency('guard')
|
23
|
+
s.add_development_dependency('guard-rspec')
|
24
|
+
s.add_development_dependency('guard-bundler')
|
25
|
+
s.add_development_dependency('rb-fsevent')
|
26
|
+
s.add_development_dependency('awesome_print')
|
27
|
+
s.add_dependency('RedCloth')
|
28
|
+
s.add_dependency('nokogiri')
|
29
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
module ElVallenato
|
4
|
+
class Letra
|
5
|
+
|
6
|
+
attr_reader :content
|
7
|
+
|
8
|
+
def initialize(content)
|
9
|
+
@content = content
|
10
|
+
@doc = Nokogiri::HTML(@content)
|
11
|
+
end
|
12
|
+
|
13
|
+
def title
|
14
|
+
@title ||= @doc.at(".text_title").text
|
15
|
+
end
|
16
|
+
|
17
|
+
def body
|
18
|
+
@body ||= @doc.search("td .text_std")[6].inner_html
|
19
|
+
end
|
20
|
+
|
21
|
+
def composer
|
22
|
+
@composer ||= @doc.search("td .text_std")[9].text
|
23
|
+
end
|
24
|
+
|
25
|
+
def artist
|
26
|
+
@artist ||= @doc.search("td .text_std")[8].text
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require 'cgi'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'URI'
|
4
|
+
|
5
|
+
module ElVallenato
|
6
|
+
|
7
|
+
class Search
|
8
|
+
attr_reader :mode,:term,:url
|
9
|
+
|
10
|
+
def initialize(mode,term)
|
11
|
+
@current_link = 0
|
12
|
+
@mode = CGI.escape(mode)
|
13
|
+
@term = CGI.escape(term)
|
14
|
+
@url = "http://www.elvallenato.com/letras/busqueda.php?x=#{@term}&busca=#{@mode}&image.x=12&image.y=11"
|
15
|
+
@base = "http://" + URI.parse(@url).host
|
16
|
+
end
|
17
|
+
|
18
|
+
def content
|
19
|
+
@content ||= OpenURI.open_uri(@url).read
|
20
|
+
end
|
21
|
+
|
22
|
+
def next_url
|
23
|
+
return nil if @current_link == pages
|
24
|
+
if @current_link > 0
|
25
|
+
link = @all_links[@current_link]["href"]
|
26
|
+
@current_link += 1
|
27
|
+
return [@base,link].join("/")
|
28
|
+
else
|
29
|
+
@all_links ||= Nokogiri::HTML.parse(content).css("span.class5 a")
|
30
|
+
link = @all_links[0]["href"]
|
31
|
+
@current_link += 1
|
32
|
+
return [@base,link].join("/")
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
36
|
+
def pages
|
37
|
+
links.size
|
38
|
+
end
|
39
|
+
|
40
|
+
def links
|
41
|
+
@page_links ||= Nokogiri::HTML.parse(content).css("span.class5 a").collect do |e|
|
42
|
+
e["href"] if e["href"] =~ /pg=\d+$/
|
43
|
+
end.compact.sort.uniq
|
44
|
+
end
|
45
|
+
|
46
|
+
def liric_links
|
47
|
+
@liric_links ||= Nokogiri::HTML.parse(content).css('.class10 a').collect do |e|
|
48
|
+
clean_url(e["href"])
|
49
|
+
end.compact.sort.uniq
|
50
|
+
end
|
51
|
+
|
52
|
+
def clean_url(url)
|
53
|
+
url =~ /letras\/letras\/(\d+)\/(.+?)$/
|
54
|
+
id = $1
|
55
|
+
song_name = CGI.escape($2)
|
56
|
+
[@base,"letras","letras",id,song_name].join("/")
|
57
|
+
end
|
58
|
+
|
59
|
+
def letras
|
60
|
+
liric_links.collect do |link|
|
61
|
+
Letra.new(OpenURI.open_uri(link).read)
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
data/lib/elvallenato.rb
ADDED