beatport_play-scraper 0.1.0
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/.gitignore +61 -0
- data/Gemfile +3 -0
- data/README.md +24 -0
- data/beatport_play-scraper.gemspec +24 -0
- data/lib/beatport_play-scraper/scraper.rb +24 -0
- data/lib/beatport_play-scraper/version.rb +5 -0
- data/lib/beatport_play-scraper.rb +1 -0
- data/spec/scraper_spec.rb +18 -0
- data/spec/spec_helper.rb +17 -0
- metadata +95 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e75138c2d5f1402ec10f217b80e0f104fa249096
|
4
|
+
data.tar.gz: 3936bcd093310fc2027637fedc18beedaeaaa792
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 5be6070deead4274d9e48c7101bb49a6d8dfb5f5ad549f2aaf9cbd0ccb38c0f8ece4453bee3e4661c53b2fec5b68ba9b073f3fd24469d3460a4b4c5bf20915da
|
7
|
+
data.tar.gz: 68ad6ca817778e87c22246c505a5cf77a721c7d2b95e017d46ade0f313fba6c9ebf55bfe7cb45bcb01b7a4d33420c3c321501423b16b1fca823131b30697e287
|
data/.gitignore
ADDED
@@ -0,0 +1,61 @@
|
|
1
|
+
# Created by http://www.gitignore.io
|
2
|
+
|
3
|
+
### Linux ###
|
4
|
+
*~
|
5
|
+
|
6
|
+
# KDE directory preferences
|
7
|
+
.directory
|
8
|
+
|
9
|
+
|
10
|
+
### Ruby ###
|
11
|
+
*.gem
|
12
|
+
*.rbc
|
13
|
+
/.config
|
14
|
+
/coverage/
|
15
|
+
/InstalledFiles
|
16
|
+
/pkg/
|
17
|
+
/spec/reports/
|
18
|
+
/test/tmp/
|
19
|
+
/test/version_tmp/
|
20
|
+
/tmp/
|
21
|
+
|
22
|
+
## Specific to RubyMotion:
|
23
|
+
.dat*
|
24
|
+
.repl_history
|
25
|
+
build/
|
26
|
+
|
27
|
+
## Documentation cache and generated files:
|
28
|
+
/.yardoc/
|
29
|
+
/_yardoc/
|
30
|
+
/doc/
|
31
|
+
/rdoc/
|
32
|
+
|
33
|
+
## Environment normalisation:
|
34
|
+
/.bundle/
|
35
|
+
/lib/bundler/man/
|
36
|
+
|
37
|
+
# for a library or gem, you might want to ignore these files since the code is
|
38
|
+
# intended to run in multiple environments; otherwise, check them in:
|
39
|
+
Gemfile.lock
|
40
|
+
.ruby-version
|
41
|
+
.ruby-gemset
|
42
|
+
|
43
|
+
# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
|
44
|
+
.rvmrc
|
45
|
+
|
46
|
+
|
47
|
+
### OSX ###
|
48
|
+
.DS_Store
|
49
|
+
.AppleDouble
|
50
|
+
.LSOverride
|
51
|
+
|
52
|
+
# Icon must ends with two \r.
|
53
|
+
Icon
|
54
|
+
|
55
|
+
|
56
|
+
# Thumbnails
|
57
|
+
._*
|
58
|
+
|
59
|
+
# Files that might appear on external disk
|
60
|
+
.Spotlight-V100
|
61
|
+
.Trashes
|
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
BeatportPlay-Scraper
|
2
|
+
---
|
3
|
+
|
4
|
+
Gets the song names from the Beatport Top 10.
|
5
|
+
|
6
|
+
# Install
|
7
|
+
|
8
|
+
`gem install beatport_play-scraper`
|
9
|
+
|
10
|
+
# Usage
|
11
|
+
|
12
|
+
```ruby
|
13
|
+
require 'beatport_play-scraper'
|
14
|
+
|
15
|
+
BeatportPlay::Scraper.get_top_10 # Returns an Enumerable with 10 strings.
|
16
|
+
```
|
17
|
+
|
18
|
+
# Input
|
19
|
+
|
20
|
+
HTML string from [beatport.com](beatport.com/).
|
21
|
+
|
22
|
+
# Output
|
23
|
+
|
24
|
+
An enumerable of the Beatport Top 10 song titles as strings.
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'beatport_play-scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'beatport_play-scraper'
|
8
|
+
spec.version = BeatportPlay::Scraper::VERSION
|
9
|
+
spec.authors = ['crzrcn']
|
10
|
+
spec.email = ['fernanlink@gmail.com']
|
11
|
+
spec.description = %q{A scraper for the Beatport Top 10}
|
12
|
+
spec.summary = %q{A scraper for the Beatport Top 10 that returns song names}
|
13
|
+
spec.homepage = 'https://github.com/crzrcn/BeatportPlay-Scraper'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
|
21
|
+
spec.add_runtime_dependency 'nokogiri', '~> 1.6', '>= 1.6.1'
|
22
|
+
|
23
|
+
spec.add_development_dependency 'rspec', '~> 2.14', '>= 2.14.1'
|
24
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'json'
|
4
|
+
|
5
|
+
module BeatportPlay
|
6
|
+
module Scraper
|
7
|
+
# Returns an enumerable containing the title of each song in the Beatport Top 10.
|
8
|
+
def self.get_top_10
|
9
|
+
song_titles = []
|
10
|
+
|
11
|
+
doc = Nokogiri::HTML(open('http://beatport.com'))
|
12
|
+
|
13
|
+
# Every Beatport Top 10 song has a div.playWrapper that has a child
|
14
|
+
# span.play-queue.play-queue-medium element with a json-data attribute that
|
15
|
+
# contains all the song data.
|
16
|
+
doc.css('div.playWrapper > span.play-queue.play-queue-medium').each do |song|
|
17
|
+
# In here we have access to the 'data-json' attribute of each song.
|
18
|
+
song_titles << JSON.parse(song['data-json'])['title']
|
19
|
+
end
|
20
|
+
|
21
|
+
song_titles
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
require 'beatport_play-scraper/scraper'
|
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'beatport_play-scraper'
|
3
|
+
|
4
|
+
describe 'BeatportPlay-Scraper' do
|
5
|
+
it 'scrapes the HTML of beatport.com, and returns a collection with the song names in Beatport Top 10' do
|
6
|
+
songs = BeatportPlay::Scraper.get_top_10
|
7
|
+
|
8
|
+
if not songs.is_a? Enumerable and songs.length == 10
|
9
|
+
return false
|
10
|
+
else
|
11
|
+
songs.each do |s|
|
12
|
+
if not s.is_a? String
|
13
|
+
return false
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
2
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
3
|
+
# Require this file using `require "spec_helper"` to ensure that it is only
|
4
|
+
# loaded once.
|
5
|
+
#
|
6
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
7
|
+
RSpec.configure do |config|
|
8
|
+
config.treat_symbols_as_metadata_keys_with_true_values = true
|
9
|
+
config.run_all_when_everything_filtered = true
|
10
|
+
config.filter_run :focus
|
11
|
+
|
12
|
+
# Run specs in random order to surface order dependencies. If you find an
|
13
|
+
# order dependency and want to debug it, you can fix the order by providing
|
14
|
+
# the seed, which is printed after each run.
|
15
|
+
# --seed 1234
|
16
|
+
config.order = 'random'
|
17
|
+
end
|
metadata
ADDED
@@ -0,0 +1,95 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: beatport_play-scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- crzrcn
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-03-26 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 1.6.1
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - "~>"
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.6'
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 1.6.1
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: rspec
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - "~>"
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: '2.14'
|
40
|
+
- - ">="
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: 2.14.1
|
43
|
+
type: :development
|
44
|
+
prerelease: false
|
45
|
+
version_requirements: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - "~>"
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: '2.14'
|
50
|
+
- - ">="
|
51
|
+
- !ruby/object:Gem::Version
|
52
|
+
version: 2.14.1
|
53
|
+
description: A scraper for the Beatport Top 10
|
54
|
+
email:
|
55
|
+
- fernanlink@gmail.com
|
56
|
+
executables: []
|
57
|
+
extensions: []
|
58
|
+
extra_rdoc_files: []
|
59
|
+
files:
|
60
|
+
- ".gitignore"
|
61
|
+
- Gemfile
|
62
|
+
- README.md
|
63
|
+
- beatport_play-scraper.gemspec
|
64
|
+
- lib/beatport_play-scraper.rb
|
65
|
+
- lib/beatport_play-scraper/scraper.rb
|
66
|
+
- lib/beatport_play-scraper/version.rb
|
67
|
+
- spec/scraper_spec.rb
|
68
|
+
- spec/spec_helper.rb
|
69
|
+
homepage: https://github.com/crzrcn/BeatportPlay-Scraper
|
70
|
+
licenses:
|
71
|
+
- MIT
|
72
|
+
metadata: {}
|
73
|
+
post_install_message:
|
74
|
+
rdoc_options: []
|
75
|
+
require_paths:
|
76
|
+
- lib
|
77
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - ">="
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '0'
|
82
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
83
|
+
requirements:
|
84
|
+
- - ">="
|
85
|
+
- !ruby/object:Gem::Version
|
86
|
+
version: '0'
|
87
|
+
requirements: []
|
88
|
+
rubyforge_project:
|
89
|
+
rubygems_version: 2.2.2
|
90
|
+
signing_key:
|
91
|
+
specification_version: 4
|
92
|
+
summary: A scraper for the Beatport Top 10 that returns song names
|
93
|
+
test_files:
|
94
|
+
- spec/scraper_spec.rb
|
95
|
+
- spec/spec_helper.rb
|