board_game_geek 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +2 -0
- data/Gemfile +2 -0
- data/Gemfile.lock +28 -0
- data/Rakefile +14 -0
- data/board_game_geek.gemspec +27 -0
- data/lib/board_game_geek/version.rb +3 -0
- data/lib/board_game_geek.rb +56 -0
- data/pkg/board_game_geek-0.0.1.gem +0 -0
- data/spec/scraper_spec.rb +62 -0
- data/spec/spec_helper.rb +20 -0
- metadata +119 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
board_game_geek (0.0.1)
|
5
|
+
nokogiri
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: http://rubygems.org/
|
9
|
+
specs:
|
10
|
+
addressable (2.2.6)
|
11
|
+
crack (0.3.1)
|
12
|
+
minitest (2.8.0)
|
13
|
+
nokogiri (1.5.0)
|
14
|
+
rake (0.9.2.2)
|
15
|
+
vcr (1.11.3)
|
16
|
+
webmock (1.7.7)
|
17
|
+
addressable (~> 2.2, > 2.2.5)
|
18
|
+
crack (>= 0.1.7)
|
19
|
+
|
20
|
+
PLATFORMS
|
21
|
+
ruby
|
22
|
+
|
23
|
+
DEPENDENCIES
|
24
|
+
board_game_geek!
|
25
|
+
minitest
|
26
|
+
rake
|
27
|
+
vcr
|
28
|
+
webmock
|
data/Rakefile
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
### Gem Development/Management
|
2
|
+
require 'bundler'
|
3
|
+
Bundler::GemHelper.install_tasks
|
4
|
+
|
5
|
+
|
6
|
+
### Spec Runner
|
7
|
+
require 'rake/testtask'
|
8
|
+
Rake::TestTask.new :spec do |t|
|
9
|
+
t.libs << "spec"
|
10
|
+
t.pattern = "spec/*_spec.rb"
|
11
|
+
t.verbose = true
|
12
|
+
end
|
13
|
+
|
14
|
+
task :default => :spec
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "board_game_geek/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "board_game_geek"
|
7
|
+
s.version = BoardGameGeek::VERSION
|
8
|
+
s.platform = Gem::Platform::RUBY
|
9
|
+
s.authors = ["Loren Norman"]
|
10
|
+
s.email = ["lorennorman@gmail.com"]
|
11
|
+
s.homepage = "http://github.com/lorennorman/board_game_geek"
|
12
|
+
s.summary = %q{BoardGameGeek.com scraper}
|
13
|
+
s.description = %q{We love board games. We love coding. Let's code against the data from BoardGameGeek.com!}
|
14
|
+
|
15
|
+
s.rubyforge_project = "board_game_geek"
|
16
|
+
|
17
|
+
s.add_dependency "nokogiri"
|
18
|
+
s.add_development_dependency "minitest"
|
19
|
+
s.add_development_dependency "vcr"
|
20
|
+
s.add_development_dependency "webmock"
|
21
|
+
s.add_development_dependency "rake"
|
22
|
+
|
23
|
+
s.files = `git ls-files`.split("\n")
|
24
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
25
|
+
# s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
26
|
+
s.require_paths = ["lib"]
|
27
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
require "bundler/setup"
|
2
|
+
require "nokogiri"
|
3
|
+
require "open-uri"
|
4
|
+
require "ostruct"
|
5
|
+
|
6
|
+
module BoardGameGeek
|
7
|
+
class Scraper
|
8
|
+
RANKED_GAMES_URI = 'http://boardgamegeek.com/browse/boardgame/page/'
|
9
|
+
GAMES_PER_PAGE = 100
|
10
|
+
|
11
|
+
def self.top_games how_many
|
12
|
+
# break total into pages + remainder
|
13
|
+
full_pages, remainder = self.break_down_total(how_many)
|
14
|
+
# accumulate #{pages} calls to bgg
|
15
|
+
# accumulate one more call(#{remainder}) to bgg
|
16
|
+
|
17
|
+
Array.new.tap do |games|
|
18
|
+
(1..(full_pages)).each do |page_number|
|
19
|
+
how_many = GAMES_PER_PAGE
|
20
|
+
how_many = remainder if page_number == full_pages && remainder > 0
|
21
|
+
|
22
|
+
doc = Nokogiri::HTML(open "#{RANKED_GAMES_URI}#{page_number}.html")
|
23
|
+
|
24
|
+
doc.css('table#collectionitems tr').each_with_index do |game_row, idx|
|
25
|
+
next if idx == 0
|
26
|
+
break if idx > how_many
|
27
|
+
|
28
|
+
cells = game_row.css("td").map(&:inner_text).map(&:strip)
|
29
|
+
|
30
|
+
name_and_date = cells[2].to_s.split("\n")
|
31
|
+
|
32
|
+
ranking = cells[0]
|
33
|
+
name = name_and_date[0]
|
34
|
+
release_date = name_and_date[2].to_s.strip[1..-2]
|
35
|
+
rating = cells[3]
|
36
|
+
|
37
|
+
image_url = game_row.css(".collection_thumbnail img").first["src"]
|
38
|
+
image_url.sub!("_mt", "_t")
|
39
|
+
|
40
|
+
games << OpenStruct.new(name: name,
|
41
|
+
ranking: ranking,
|
42
|
+
rating: rating,
|
43
|
+
release_date: release_date,
|
44
|
+
image_url: image_url)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def self.break_down_total total
|
51
|
+
[(total.to_f/GAMES_PER_PAGE).ceil, total%GAMES_PER_PAGE]
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
BGG = BoardGameGeek
|
Binary file
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require "spec_helper"
|
2
|
+
|
3
|
+
describe BGG::Scraper do
|
4
|
+
subject { BGG::Scraper }
|
5
|
+
|
6
|
+
after do
|
7
|
+
VCR.eject_cassette
|
8
|
+
end
|
9
|
+
|
10
|
+
describe "breaking a total into pages and remainder" do
|
11
|
+
data = { 1 => [ 1, 1 ],
|
12
|
+
50 => [ 1, 50 ],
|
13
|
+
100 => [ 1, 0 ],
|
14
|
+
101 => [ 2, 1 ],
|
15
|
+
199 => [ 2, 99 ],
|
16
|
+
200 => [ 2, 0 ],
|
17
|
+
201 => [ 3, 1 ],
|
18
|
+
999 => [ 10, 99 ],
|
19
|
+
1000 => [ 10, 0 ],
|
20
|
+
1001 => [ 11, 1 ] }
|
21
|
+
|
22
|
+
data.each do |total, desired_results|
|
23
|
+
pages, remainder = desired_results
|
24
|
+
|
25
|
+
it "breaks a total of #{total} into #{pages} pages and #{remainder} remainder" do
|
26
|
+
final_pages, final_remainder = subject.break_down_total(total)
|
27
|
+
final_pages.must_be :==, pages
|
28
|
+
final_remainder.must_be :==, remainder
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
describe "a game record" do
|
34
|
+
before do
|
35
|
+
VCR.insert_cassette('board_game_geek_1')
|
36
|
+
end
|
37
|
+
|
38
|
+
let(:first_game) { subject.top_games(1).first }
|
39
|
+
|
40
|
+
it "exposes some handy attributes" do
|
41
|
+
first_game.must_respond_to :name
|
42
|
+
first_game.must_respond_to :image_url
|
43
|
+
first_game.must_respond_to :rating
|
44
|
+
first_game.must_respond_to :ranking
|
45
|
+
first_game.must_respond_to :release_date
|
46
|
+
end
|
47
|
+
|
48
|
+
it "correctly parses the image source" do
|
49
|
+
first_game.image_url.must_be :==, "http://cf.geekdo-images.com/images/pic361592_t.jpg"
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
it "gets the top 100 games" do
|
54
|
+
VCR.insert_cassette('board_game_geek_100')
|
55
|
+
subject.top_games(100).length.must_be :==, 100
|
56
|
+
end
|
57
|
+
|
58
|
+
it "gets the top 1000 games" do
|
59
|
+
VCR.insert_cassette('board_game_geek_1000')
|
60
|
+
subject.top_games(1000).length.must_be :==, 1000
|
61
|
+
end
|
62
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
require "bundler/setup"
|
2
|
+
|
3
|
+
# MiniTest
|
4
|
+
require "minitest/autorun"
|
5
|
+
# require 'minitest/reporters'
|
6
|
+
# MiniTest::Unit.runner = MiniTest::SuiteRunner.new
|
7
|
+
# MiniTest::Unit.runner.reporters << MiniTest::Reporters::SpecReporter.new
|
8
|
+
|
9
|
+
# VCR
|
10
|
+
require "vcr"
|
11
|
+
|
12
|
+
VCR.config do |c|
|
13
|
+
c.cassette_library_dir = 'spec/vcr_cassettes'
|
14
|
+
c.stub_with :webmock
|
15
|
+
end
|
16
|
+
|
17
|
+
# System Under Test
|
18
|
+
require "board_game_geek"
|
19
|
+
|
20
|
+
|
metadata
ADDED
@@ -0,0 +1,119 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: board_game_geek
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Loren Norman
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-11-13 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: &2153892060 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *2153892060
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: minitest
|
27
|
+
requirement: &2153891500 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *2153891500
|
36
|
+
- !ruby/object:Gem::Dependency
|
37
|
+
name: vcr
|
38
|
+
requirement: &2153891040 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ! '>='
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
44
|
+
type: :development
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: *2153891040
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: webmock
|
49
|
+
requirement: &2153890620 !ruby/object:Gem::Requirement
|
50
|
+
none: false
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
type: :development
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *2153890620
|
58
|
+
- !ruby/object:Gem::Dependency
|
59
|
+
name: rake
|
60
|
+
requirement: &2153890200 !ruby/object:Gem::Requirement
|
61
|
+
none: false
|
62
|
+
requirements:
|
63
|
+
- - ! '>='
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: '0'
|
66
|
+
type: :development
|
67
|
+
prerelease: false
|
68
|
+
version_requirements: *2153890200
|
69
|
+
description: We love board games. We love coding. Let's code against the data from
|
70
|
+
BoardGameGeek.com!
|
71
|
+
email:
|
72
|
+
- lorennorman@gmail.com
|
73
|
+
executables: []
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- .gitignore
|
78
|
+
- Gemfile
|
79
|
+
- Gemfile.lock
|
80
|
+
- Rakefile
|
81
|
+
- board_game_geek.gemspec
|
82
|
+
- lib/board_game_geek.rb
|
83
|
+
- lib/board_game_geek/version.rb
|
84
|
+
- pkg/board_game_geek-0.0.1.gem
|
85
|
+
- spec/scraper_spec.rb
|
86
|
+
- spec/spec_helper.rb
|
87
|
+
homepage: http://github.com/lorennorman/board_game_geek
|
88
|
+
licenses: []
|
89
|
+
post_install_message:
|
90
|
+
rdoc_options: []
|
91
|
+
require_paths:
|
92
|
+
- lib
|
93
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
94
|
+
none: false
|
95
|
+
requirements:
|
96
|
+
- - ! '>='
|
97
|
+
- !ruby/object:Gem::Version
|
98
|
+
version: '0'
|
99
|
+
segments:
|
100
|
+
- 0
|
101
|
+
hash: 2103976381804118628
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
none: false
|
104
|
+
requirements:
|
105
|
+
- - ! '>='
|
106
|
+
- !ruby/object:Gem::Version
|
107
|
+
version: '0'
|
108
|
+
segments:
|
109
|
+
- 0
|
110
|
+
hash: 2103976381804118628
|
111
|
+
requirements: []
|
112
|
+
rubyforge_project: board_game_geek
|
113
|
+
rubygems_version: 1.8.10
|
114
|
+
signing_key:
|
115
|
+
specification_version: 3
|
116
|
+
summary: BoardGameGeek.com scraper
|
117
|
+
test_files:
|
118
|
+
- spec/scraper_spec.rb
|
119
|
+
- spec/spec_helper.rb
|