drummingnews_cli_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 +9 -0
- data/Gemfile +8 -0
- data/LICENSE.txt +21 -0
- data/README.md +19 -0
- data/Rakefile +2 -0
- data/bin/console +21 -0
- data/bin/drummingnews +17 -0
- data/bin/setup +8 -0
- data/drummingnews_cli_scraper.gemspec +35 -0
- data/lib/drummingnews_cli_scraper.rb +11 -0
- data/lib/drummingnews_cli_scraper/article.rb +12 -0
- data/lib/drummingnews_cli_scraper/cli.rb +75 -0
- data/lib/drummingnews_cli_scraper/magazine.rb +21 -0
- data/lib/drummingnews_cli_scraper/scraper.rb +68 -0
- data/lib/drummingnews_cli_scraper/version.rb +3 -0
- data/spec.md +7 -0
- metadata +124 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 77695d5cba67a4144b5291f2363aee3a345a97f2
|
4
|
+
data.tar.gz: f7efb7641752bf13cac23290ff80dfbe20b20250
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 4437a1a8cb3c71fea5547cc0fab5aaf4d4bc2e044fe23b88d2a423134c4274f648f34c08d28527f92a4a615f7aee27fda3a22ed74e5b72b5f6ab3a5a04517222
|
7
|
+
data.tar.gz: 3fead02a7cc7b2dc6dfb370aa843cad68dfd1b2e0cdd508ce6a439bfbcf5087a1531ce5d9e0a8bffd4cd8be7468614567115e6b007df49ea8cdb04cbd9bd4948
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 TODO: Write your name
|
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 +1,19 @@
|
|
1
|
+
# DrummingnewsCliScraper
|
2
|
+
|
3
|
+
A command line gem that scrapes several drumming publications and displays their contents.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
$ gem install drummingnews_cli_scraper
|
8
|
+
|
9
|
+
## Usage
|
10
|
+
|
11
|
+
Run `drummingnews` to start the interface. You'll see a list of available publications to choose from. Enter the one you'd like to view. This will display the current articles for that magazine. Enter the number for your choice and it will print out.
|
12
|
+
|
13
|
+
## Contributing
|
14
|
+
|
15
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/bretburau/drummingnews_cli_scraper.
|
16
|
+
|
17
|
+
## License
|
18
|
+
|
19
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'pry'
|
4
|
+
require 'nokogiri'
|
5
|
+
require 'open-uri'
|
6
|
+
require "bundler/setup"
|
7
|
+
require "drummingnews_cli_scraper"
|
8
|
+
|
9
|
+
Modern_drummer = DrummingNews::Magazine.new("Modern Drummer")
|
10
|
+
DRUM = DrummingNews::Magazine.new("DRUM!")
|
11
|
+
Rhythm = DrummingNews::Magazine.new("Rhythm Magazine")
|
12
|
+
Scraper = DrummingNews::Scraper.new
|
13
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
14
|
+
# with your gem easier. You can also use a different console, if you like.
|
15
|
+
|
16
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
17
|
+
# require "pry"
|
18
|
+
# Pry.start
|
19
|
+
|
20
|
+
require "irb"
|
21
|
+
IRB.start(__FILE__)
|
data/bin/drummingnews
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'pry'
|
4
|
+
require 'nokogiri'
|
5
|
+
require 'open-uri'
|
6
|
+
require_relative '../lib/drummingnews_cli_scraper.rb'
|
7
|
+
puts "\n**********************************\n"
|
8
|
+
puts "Welcome to your drumming newsfeed!"
|
9
|
+
puts "**********************************"
|
10
|
+
|
11
|
+
Modern_drummer = DrummingNews::Magazine.new("Modern Drummer")
|
12
|
+
DRUM = DrummingNews::Magazine.new("DRUM!")
|
13
|
+
Rhythm = DrummingNews::Magazine.new("Rhythm Magazine")
|
14
|
+
|
15
|
+
DrummingNews::CLI.new.start
|
16
|
+
|
17
|
+
|
data/bin/setup
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "drummingnews_cli_scraper/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "drummingnews_cli_scraper"
|
8
|
+
spec.version = DrummingnewsCliScraper::VERSION
|
9
|
+
spec.authors = ["Bret Burau"]
|
10
|
+
spec.email = ["burhooo@gmail.com"]
|
11
|
+
spec.summary = "Scraper CLI to display articles for several drumming publications."
|
12
|
+
spec.homepage = "https://github.com/bretburau/drummingnews_cli_scraper"
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
16
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
17
|
+
if spec.respond_to?(:metadata)
|
18
|
+
spec.metadata["allowed_push_host"] = "https://rubygems.org"
|
19
|
+
else
|
20
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
21
|
+
"public gem pushes."
|
22
|
+
end
|
23
|
+
|
24
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
25
|
+
f.match(%r{^(test|spec|features)/})
|
26
|
+
end
|
27
|
+
spec.bindir = "bin"
|
28
|
+
spec.executables = ["drummingnews"]#spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
29
|
+
spec.require_paths = ["lib"]
|
30
|
+
|
31
|
+
spec.add_runtime_dependency "pry", '~> 0.10.4'
|
32
|
+
spec.add_runtime_dependency 'nokogiri', '~> 1.8', '>= 1.8.1'
|
33
|
+
spec.add_development_dependency "bundler", "~> 1.15"
|
34
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
35
|
+
end
|
@@ -0,0 +1,11 @@
|
|
1
|
+
|
2
|
+
|
3
|
+
|
4
|
+
module DrummingNews
|
5
|
+
require_relative "drummingnews_cli_scraper/version"
|
6
|
+
require_relative 'drummingnews_cli_scraper/cli.rb'
|
7
|
+
require_relative 'drummingnews_cli_scraper/scraper.rb'
|
8
|
+
require_relative 'drummingnews_cli_scraper/article.rb'
|
9
|
+
require_relative 'drummingnews_cli_scraper/magazine.rb'
|
10
|
+
end
|
11
|
+
|
@@ -0,0 +1,75 @@
|
|
1
|
+
class DrummingNews::CLI
|
2
|
+
attr_accessor :articles, :current_magazine
|
3
|
+
|
4
|
+
def start
|
5
|
+
@scraper = DrummingNews::Scraper.new #Instansiate scraper
|
6
|
+
@scraper.scrape_md
|
7
|
+
@scraper.scrape_drum
|
8
|
+
@scraper.scrape_rhythm
|
9
|
+
call
|
10
|
+
end
|
11
|
+
|
12
|
+
def call
|
13
|
+
choose_mag
|
14
|
+
list_articles
|
15
|
+
choose_article
|
16
|
+
end
|
17
|
+
|
18
|
+
def choose_mag
|
19
|
+
puts "Which site's articles would you like to view?"
|
20
|
+
puts "1. Modern Drummer"
|
21
|
+
puts "2. DRUM!"
|
22
|
+
puts "3. Rhythm Magazine"
|
23
|
+
puts "Or 'exit' to quit"
|
24
|
+
mag_choice = ""
|
25
|
+
mag_choice = gets.strip
|
26
|
+
case mag_choice.downcase
|
27
|
+
when "1"
|
28
|
+
@articles = Modern_drummer.articles ###Find magazine by title and get articles
|
29
|
+
@current_magazine = Modern_drummer
|
30
|
+
when "2"
|
31
|
+
@articles = DRUM.articles
|
32
|
+
@current_magazine = DRUM
|
33
|
+
when "3"
|
34
|
+
@articles = Rhythm.articles
|
35
|
+
@current_magazine = Rhythm
|
36
|
+
when "exit"
|
37
|
+
exit
|
38
|
+
else
|
39
|
+
puts "Please enter 1-3 or 'exit'"
|
40
|
+
choose_mag
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def list_articles
|
45
|
+
puts "\n------------------------------------------"
|
46
|
+
@articles.each_with_index do |article, index|
|
47
|
+
puts "#{index + 1}. #{article.title}"
|
48
|
+
end
|
49
|
+
puts "------------------------------------------\n"
|
50
|
+
end
|
51
|
+
|
52
|
+
def choose_article
|
53
|
+
puts "Which one would you like to view? Enter 'back' to go to the main menu, or 'exit' to quit"
|
54
|
+
article_choice = gets.strip
|
55
|
+
until article_choice.to_i.between?(1, 10) || article_choice.downcase == "back" || article_choice.downcase == "exit" do ###Probably gonna need to change condition to a .length or something
|
56
|
+
puts "Please enter a valid article number or 'back'"
|
57
|
+
article_choice = gets.strip
|
58
|
+
end
|
59
|
+
if article_choice.downcase == "back"
|
60
|
+
puts ""
|
61
|
+
call
|
62
|
+
elsif article_choice.downcase == "exit"
|
63
|
+
exit
|
64
|
+
else
|
65
|
+
display_article(article_choice.to_i)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def display_article(article_choice)
|
70
|
+
article_url = @current_magazine.find(article_choice).url
|
71
|
+
article_content = @scraper.scrape_article(article_url, @current_magazine)
|
72
|
+
puts article_content
|
73
|
+
call
|
74
|
+
end
|
75
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
class DrummingNews::Magazine
|
2
|
+
attr_accessor :name, :articles
|
3
|
+
@@all = []
|
4
|
+
def initialize(name)
|
5
|
+
@articles = []
|
6
|
+
@name = name
|
7
|
+
@@all << self
|
8
|
+
end
|
9
|
+
|
10
|
+
def self.create(name)
|
11
|
+
self.new(name)
|
12
|
+
end
|
13
|
+
|
14
|
+
def find(num)
|
15
|
+
@articles[num-1]
|
16
|
+
end
|
17
|
+
|
18
|
+
def self.all
|
19
|
+
@@all
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,68 @@
|
|
1
|
+
class DrummingNews::Scraper
|
2
|
+
attr_accessor :magazines
|
3
|
+
|
4
|
+
def scrape_md
|
5
|
+
html = open("https://www.moderndrummer.com/")
|
6
|
+
doc = Nokogiri::HTML(html)
|
7
|
+
doc.css("div.article").first(10).each do |scrape|
|
8
|
+
article = DrummingNews::Article.new
|
9
|
+
article.title = scrape.css("a.inline-link").text
|
10
|
+
article.url = scrape.css("a.inline-link").attribute("href").value
|
11
|
+
article.magazine = Modern_drummer
|
12
|
+
Modern_drummer.articles << article
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
def scrape_drum
|
17
|
+
html = open("http://drummagazine.com/news/")
|
18
|
+
doc = Nokogiri::HTML(html)
|
19
|
+
doc.css("h2.cb-post-title").each do |scrape|
|
20
|
+
article = DrummingNews::Article.new
|
21
|
+
article.title = scrape.text
|
22
|
+
article.url = scrape.css("a").attribute("href").value
|
23
|
+
article.magazine = DRUM
|
24
|
+
DRUM.articles << article
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def scrape_rhythm
|
29
|
+
html = open("http://www.musicradar.com/rhythm")
|
30
|
+
doc = Nokogiri::HTML(html)
|
31
|
+
doc.css(".feature-block a").each do |scrape| #Scrapes header titles
|
32
|
+
article = DrummingNews::Article.new
|
33
|
+
article.title = scrape.css("span.article-name").text
|
34
|
+
article.url = scrape.attribute("href").value
|
35
|
+
article.magazine = Rhythm
|
36
|
+
Rhythm.articles << article
|
37
|
+
end
|
38
|
+
doc.css(".listingResult").first(7).each do |scrape| #Scrapes the rest
|
39
|
+
article = DrummingNews::Article.new
|
40
|
+
article.title = scrape.css("h3").text
|
41
|
+
article.url = scrape.css("a").attribute("href")
|
42
|
+
article.magazine = Rhythm
|
43
|
+
Rhythm.articles << article
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
def scrape_article(url, current_magazine)
|
48
|
+
if current_magazine == Modern_drummer #Set up scraping for different magazines
|
49
|
+
scrape_css = ".entry-content p"
|
50
|
+
elsif current_magazine == DRUM
|
51
|
+
scrape_css = ".cb-itemprop p"
|
52
|
+
elsif current_magazine == Rhythm
|
53
|
+
scrape_css = ".gallery-text p"
|
54
|
+
end
|
55
|
+
article = ""
|
56
|
+
html = open(url)
|
57
|
+
doc = Nokogiri::HTML(html)
|
58
|
+
doc.css(scrape_css).each do |p|
|
59
|
+
article += p.text
|
60
|
+
article += "\n\n"
|
61
|
+
end
|
62
|
+
article += "------------------------------------------\n\n"
|
63
|
+
article
|
64
|
+
end
|
65
|
+
|
66
|
+
|
67
|
+
|
68
|
+
end
|
data/spec.md
ADDED
metadata
ADDED
@@ -0,0 +1,124 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: drummingnews_cli_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Bret Burau
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-11-01 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: pry
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.10.4
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.10.4
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.8'
|
34
|
+
- - ">="
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: 1.8.1
|
37
|
+
type: :runtime
|
38
|
+
prerelease: false
|
39
|
+
version_requirements: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - "~>"
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '1.8'
|
44
|
+
- - ">="
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 1.8.1
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: bundler
|
49
|
+
requirement: !ruby/object:Gem::Requirement
|
50
|
+
requirements:
|
51
|
+
- - "~>"
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '1.15'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '1.15'
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
name: rake
|
63
|
+
requirement: !ruby/object:Gem::Requirement
|
64
|
+
requirements:
|
65
|
+
- - "~>"
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '10.0'
|
68
|
+
type: :development
|
69
|
+
prerelease: false
|
70
|
+
version_requirements: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - "~>"
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '10.0'
|
75
|
+
description:
|
76
|
+
email:
|
77
|
+
- burhooo@gmail.com
|
78
|
+
executables:
|
79
|
+
- drummingnews
|
80
|
+
extensions: []
|
81
|
+
extra_rdoc_files: []
|
82
|
+
files:
|
83
|
+
- ".gitignore"
|
84
|
+
- Gemfile
|
85
|
+
- LICENSE.txt
|
86
|
+
- README.md
|
87
|
+
- Rakefile
|
88
|
+
- bin/console
|
89
|
+
- bin/drummingnews
|
90
|
+
- bin/setup
|
91
|
+
- drummingnews_cli_scraper.gemspec
|
92
|
+
- lib/drummingnews_cli_scraper.rb
|
93
|
+
- lib/drummingnews_cli_scraper/article.rb
|
94
|
+
- lib/drummingnews_cli_scraper/cli.rb
|
95
|
+
- lib/drummingnews_cli_scraper/magazine.rb
|
96
|
+
- lib/drummingnews_cli_scraper/scraper.rb
|
97
|
+
- lib/drummingnews_cli_scraper/version.rb
|
98
|
+
- spec.md
|
99
|
+
homepage: https://github.com/bretburau/drummingnews_cli_scraper
|
100
|
+
licenses:
|
101
|
+
- MIT
|
102
|
+
metadata:
|
103
|
+
allowed_push_host: https://rubygems.org
|
104
|
+
post_install_message:
|
105
|
+
rdoc_options: []
|
106
|
+
require_paths:
|
107
|
+
- lib
|
108
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
109
|
+
requirements:
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: '0'
|
113
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
requirements: []
|
119
|
+
rubyforge_project:
|
120
|
+
rubygems_version: 2.6.7
|
121
|
+
signing_key:
|
122
|
+
specification_version: 4
|
123
|
+
summary: Scraper CLI to display articles for several drumming publications.
|
124
|
+
test_files: []
|