mixcloud_parser 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 +9 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +45 -0
- data/Rakefile +1 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/lib/mixcloud_parser.rb +7 -0
- data/lib/mixcloud_parser/parser.rb +80 -0
- data/lib/mixcloud_parser/version.rb +3 -0
- data/mixcloud_parser.gemspec +27 -0
- data/spec/mixcloud_parser_spec.rb +29 -0
- data/spec/spec_helper.rb +5 -0
- metadata +145 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 46c70a8f32ff2781835e3995bb1e9888e1a685ee
|
4
|
+
data.tar.gz: a8a58837a9cef35625fd63ee650302df73ef6977
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e333259fb293de40f2ca2c08127aae469fc5e554b5133f010f7efe6643cdbfcae9e5a8726c6fa383694eaf20214a3ff8f1097b8a57be056ef9a9a292122881ca
|
7
|
+
data.tar.gz: 3188b3f217ee2407031867f628011948d1f42ebb8593ba48032ddd48d1507ac5d7132defe501e9b24c8897469e3ded8bbc1da6a90b5febe47a87261f5ea3d6b4
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 TakteS
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
# MixcloudParser
|
2
|
+
|
3
|
+
Podcasts parser from mixcloud.com
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'mixcloud_parser'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install mixcloud_parser
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
gem 'mixcloud_parser'
|
25
|
+
|
26
|
+
file = MixcloudParser::Parser.new('https://www.mixcloud.com/link_to_podcast', '/path/to/your/folder')
|
27
|
+
file.parse
|
28
|
+
```
|
29
|
+
|
30
|
+
|
31
|
+
## Development
|
32
|
+
|
33
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
34
|
+
|
35
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
36
|
+
|
37
|
+
## Contributing
|
38
|
+
|
39
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/mixcloud_parser.
|
40
|
+
|
41
|
+
|
42
|
+
## License
|
43
|
+
|
44
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
45
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bundler/gem_tasks'
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "mixcloud_parser"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
module MixcloudParser
|
2
|
+
class Parser
|
3
|
+
def initialize(url, path)
|
4
|
+
@url = url
|
5
|
+
@path = path
|
6
|
+
end
|
7
|
+
|
8
|
+
# Main parser method
|
9
|
+
def parse
|
10
|
+
# Try parse file
|
11
|
+
begin
|
12
|
+
# Open browser window for getting file name and URL (Mixcloud gives link only after starting a podcast)
|
13
|
+
browser = Watir::Browser.new
|
14
|
+
browser.goto @url
|
15
|
+
|
16
|
+
# Parse the resulted page through nokogiri
|
17
|
+
page = Nokogiri::HTML(browser.html)
|
18
|
+
|
19
|
+
# Close browser
|
20
|
+
browser.close
|
21
|
+
|
22
|
+
# Get file name
|
23
|
+
filename = page.search('cloudcast-title', '//h1').last.content
|
24
|
+
|
25
|
+
puts "Downloading '#{ filename }'..."
|
26
|
+
|
27
|
+
# Get file URL
|
28
|
+
url = page.css('audio')
|
29
|
+
url = URI.extract(url.to_s).first
|
30
|
+
|
31
|
+
# Check the download
|
32
|
+
check_file(url, filename)
|
33
|
+
|
34
|
+
# Return error message and retry
|
35
|
+
rescue
|
36
|
+
puts 'Error. Retrying...'
|
37
|
+
|
38
|
+
browser.close
|
39
|
+
retry
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
private
|
44
|
+
|
45
|
+
# Checking the download
|
46
|
+
def check_file(url, filename)
|
47
|
+
# Set full file name (with path and extension)
|
48
|
+
filename = @path + filename unless filename.include?(@path)
|
49
|
+
filename += '.m4a' unless filename.include?('m4a')
|
50
|
+
|
51
|
+
# Create a path if him is not exist
|
52
|
+
FileUtils.mkdir_p(@path) unless File.directory?(@path)
|
53
|
+
|
54
|
+
# Print message if file successfuly downloaded
|
55
|
+
if File.exist?(filename) && File.size(filename) > 0
|
56
|
+
puts "#{ filename.split('/').last } successfuly downloaded!"
|
57
|
+
|
58
|
+
# Download file if him exist, but him size is 0
|
59
|
+
elsif File.exist?(filename) && File.size(filename) == 0
|
60
|
+
download_file(url, filename)
|
61
|
+
|
62
|
+
# Create and download file if him is not exist
|
63
|
+
else
|
64
|
+
File.new(filename, 'w+')
|
65
|
+
download_file(url, filename)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
# Downloading
|
70
|
+
def download_file(url, filename)
|
71
|
+
File.open(filename, 'wb') do |saved_file|
|
72
|
+
open(url) do |read_file|
|
73
|
+
saved_file.write(read_file.read)
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
check_file(url, filename)
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'mixcloud_parser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'mixcloud_parser'
|
8
|
+
spec.version = MixcloudParser::VERSION
|
9
|
+
spec.authors = ['TakteS']
|
10
|
+
spec.email = ['takt96@gmail.com']
|
11
|
+
|
12
|
+
spec.summary = %q{ Podcasts parser from mixcloud.com }
|
13
|
+
spec.homepage = 'https://github.com/TakteS/mixcloud_parser'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_development_dependency 'bundler', '~> 1.10'
|
22
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
23
|
+
spec.add_development_dependency 'rspec'
|
24
|
+
spec.add_development_dependency 'nokogiri'
|
25
|
+
spec.add_development_dependency 'watir-webdriver'
|
26
|
+
spec.add_development_dependency 'open-uri'
|
27
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe MixcloudParser do
|
4
|
+
describe 'Check file exist' do
|
5
|
+
context 'when file is downloaded' do
|
6
|
+
path = '/home/taktes/MixCloud/'
|
7
|
+
url = 'https://www.mixcloud.com/RedBullThre3style/dj-short-philippines-cebu-qualifier/'
|
8
|
+
file = MixcloudParser::Parser.new(url, path)
|
9
|
+
file.parse
|
10
|
+
|
11
|
+
it 'file exist' do
|
12
|
+
expect(File.exist?("#{ path }DJ Short | Philippines | Cebu Qualifier.m4a")).to equal(true)
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
describe 'Check file size' do
|
18
|
+
context 'when file is downloaded' do
|
19
|
+
path = '/home/taktes/MixCloud/'
|
20
|
+
url = 'https://www.mixcloud.com/RedBullThre3style/dj-short-philippines-cebu-qualifier/'
|
21
|
+
file = MixcloudParser::Parser.new(url, path)
|
22
|
+
file.parse
|
23
|
+
|
24
|
+
it 'file size > 0' do
|
25
|
+
expect(File.size("#{ path }DJ Short | Philippines | Cebu Qualifier.m4a") > 0).to equal(true)
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,145 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: mixcloud_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- TakteS
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-10-18 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.10'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.10'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: watir-webdriver
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: open-uri
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description:
|
98
|
+
email:
|
99
|
+
- takt96@gmail.com
|
100
|
+
executables:
|
101
|
+
- console
|
102
|
+
- setup
|
103
|
+
extensions: []
|
104
|
+
extra_rdoc_files: []
|
105
|
+
files:
|
106
|
+
- ".gitignore"
|
107
|
+
- Gemfile
|
108
|
+
- LICENSE.txt
|
109
|
+
- README.md
|
110
|
+
- Rakefile
|
111
|
+
- bin/console
|
112
|
+
- bin/setup
|
113
|
+
- lib/mixcloud_parser.rb
|
114
|
+
- lib/mixcloud_parser/parser.rb
|
115
|
+
- lib/mixcloud_parser/version.rb
|
116
|
+
- mixcloud_parser.gemspec
|
117
|
+
- spec/mixcloud_parser_spec.rb
|
118
|
+
- spec/spec_helper.rb
|
119
|
+
homepage: https://github.com/TakteS/mixcloud_parser
|
120
|
+
licenses:
|
121
|
+
- MIT
|
122
|
+
metadata: {}
|
123
|
+
post_install_message:
|
124
|
+
rdoc_options: []
|
125
|
+
require_paths:
|
126
|
+
- lib
|
127
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
133
|
+
requirements:
|
134
|
+
- - ">="
|
135
|
+
- !ruby/object:Gem::Version
|
136
|
+
version: '0'
|
137
|
+
requirements: []
|
138
|
+
rubyforge_project:
|
139
|
+
rubygems_version: 2.4.8
|
140
|
+
signing_key:
|
141
|
+
specification_version: 4
|
142
|
+
summary: Podcasts parser from mixcloud.com
|
143
|
+
test_files:
|
144
|
+
- spec/mixcloud_parser_spec.rb
|
145
|
+
- spec/spec_helper.rb
|