pitch_fx_scraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +8 -0
- data/lib/pitch_fx_scraper/fetch.rb +100 -0
- data/lib/pitch_fx_scraper/version.rb +3 -0
- data/lib/pitch_fx_scraper.rb +8 -0
- data/pitch_fx_scraper.gemspec +24 -0
- data/spec/fetch_spec.rb +41 -0
- data/spec/spec_helper.rb +24 -0
- metadata +100 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
NDRlMDUwY2FhMjBmYjJiNTlhZGZiNGEzOWE3NWRlMTFjYTczNDU5Yg==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
MGZmNzU3MmQ5YzhmNzRmZDg0Y2U4MTI3NGQ0NDkwNjVhNTEyNDExZg==
|
7
|
+
SHA512:
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
ODBjNDZlNGU0MzVmODgxNDJhNzA0NmUxODM1NDhiZjRhZTZiYTEwOTFmNjcw
|
10
|
+
YzY2OTI1ZTJkNjI0YzYwMDI1OWZiY2Y1ZmRiMTg5ZDAxMTY2YjUzZDBiNzY0
|
11
|
+
NjcyZjc5MDFmMWMyNjYwMjIyZWNmYTgzOTRjZWUzNzlhYzg0Zjc=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
OTg4MmYwYzhmNDdmMjk3MDI1N2I5M2ZhNTJlZGI2OTU0NmMxMzc5YzU3OWVi
|
14
|
+
ZGU5ZTgzYzNmOTc5OGY1ZmJhMjQzYWEzZjJkOTc4NzliMjc1M2ZkNjE0OTky
|
15
|
+
MWY3MDQ4ZDhjYzAwNDk2OGU3YTQzNDk5MWI3YTEzNTg5OGU2Yzg=
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 David Sachitano
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# PitchFxScraper
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'pitch_fx_scraper'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install pitch_fx_scraper
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
|
2
|
+
require 'chronic'
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'open-uri'
|
5
|
+
|
6
|
+
module Fetch
|
7
|
+
|
8
|
+
@@host_url_base = "http://gd2.mlb.com"
|
9
|
+
|
10
|
+
def Fetch.url_for_date(date, milb=false)
|
11
|
+
date_object = Chronic.parse(date)
|
12
|
+
if milb == false
|
13
|
+
url_base = @@host_url_base + "/components/game/mlb/"
|
14
|
+
else
|
15
|
+
url_base = @@host_url_base + "/components/game/milb/"
|
16
|
+
end
|
17
|
+
url_base += "year_#{"%04d" % date_object.year}/"
|
18
|
+
url_base += "month_#{"%02d" % date_object.month}/"
|
19
|
+
url_base += "day_#{"%02d" % date_object.day}"
|
20
|
+
end
|
21
|
+
|
22
|
+
|
23
|
+
## Return a list of hashes containing game data urls
|
24
|
+
## with game ids for a given date string
|
25
|
+
##
|
26
|
+
def Fetch.get_game_urls(date, milb=false)
|
27
|
+
if milb == false
|
28
|
+
master_scoreboard_url = Fetch.url_for_date(date) + "/master_scoreboard.xml"
|
29
|
+
else
|
30
|
+
master_scoreboard_url = Fetch.url_for_date(date,milb) + "/milb_master_game_file.xml"
|
31
|
+
end
|
32
|
+
|
33
|
+
scoreboard = Nokogiri::XML(open(master_scoreboard_url))
|
34
|
+
|
35
|
+
game_urls = []
|
36
|
+
|
37
|
+
scoreboard.xpath("//game").each do |node|
|
38
|
+
if milb == false
|
39
|
+
game_path = node.attr('game_data_directory')
|
40
|
+
game_id = node.attr('gameday')
|
41
|
+
game_url = @@host_url_base + game_path + "/game_events.xml"
|
42
|
+
else
|
43
|
+
game_id = node.attr('id')
|
44
|
+
game_url = node.attr('boxscore')
|
45
|
+
end
|
46
|
+
|
47
|
+
game_urls << {:game_id => game_id, :game_url => game_url}
|
48
|
+
end
|
49
|
+
|
50
|
+
return game_urls
|
51
|
+
end
|
52
|
+
|
53
|
+
## Return a list of hashes containing home team data
|
54
|
+
## for a given date string
|
55
|
+
def Fetch.get_milb_schedule (date)
|
56
|
+
game_boxscores = Fetch.get_game_urls(date, true)
|
57
|
+
|
58
|
+
games = []
|
59
|
+
|
60
|
+
game_boxscores.each do |score|
|
61
|
+
begin
|
62
|
+
boxscore = Nokogiri::XML(open(score[:game_url]))
|
63
|
+
|
64
|
+
boxscore.xpath("//boxscore").each do |node|
|
65
|
+
home_sname = node.attr('home_sname')
|
66
|
+
home_fname = node.attr('home_fname')
|
67
|
+
file_date = node.attr('date')
|
68
|
+
|
69
|
+
games << {:home_sname => home_sname, :home_fname => home_fname, :date => file_date}
|
70
|
+
end
|
71
|
+
rescue OpenURI::HTTPError => e
|
72
|
+
# oops!
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
return games
|
77
|
+
end
|
78
|
+
|
79
|
+
|
80
|
+
## expects a hash with keys {:game_id, :game_url}
|
81
|
+
##
|
82
|
+
#def Fetch.save_file_to_disk (game_hash)
|
83
|
+
# open(@@game_data_path+"/"+game_hash[:game_id]+".xml", mode = "w+") do |file|
|
84
|
+
# file << open(game_hash[:game_url]).read
|
85
|
+
# end
|
86
|
+
#end
|
87
|
+
|
88
|
+
|
89
|
+
## given a date as a string, fetch and save all
|
90
|
+
## game files to disk
|
91
|
+
##
|
92
|
+
#def Fetch.save_files_for_date (date_string)
|
93
|
+
# game_event_urls = Fetch.get_game_urls(date_string)
|
94
|
+
#
|
95
|
+
# game_event_urls.each do |game_data|
|
96
|
+
# Fetch.save_file_to_disk (game_data)
|
97
|
+
# end
|
98
|
+
#end
|
99
|
+
|
100
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'pitch_fx_scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "pitch_fx_scraper"
|
8
|
+
spec.version = PitchFxScraper::VERSION
|
9
|
+
spec.authors = ["David Sachitano"]
|
10
|
+
spec.email = ["dsachita@gmail.com"]
|
11
|
+
spec.description = %q{Utilities for grabbing various data from mlb}
|
12
|
+
spec.summary = %q{Initial release is focused on getting minimal schedule data.}
|
13
|
+
spec.homepage = "http://thebaseballrun.com"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.3"
|
23
|
+
spec.add_development_dependency "rspec", "~> 2.14"
|
24
|
+
end
|
data/spec/fetch_spec.rb
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe Fetch do
|
4
|
+
|
5
|
+
describe "url_for_date" do
|
6
|
+
it 'should return a valid url for April 3rd 2014' do
|
7
|
+
our_date = 'April 3rd 2014'
|
8
|
+
result = Fetch.url_for_date(our_date)
|
9
|
+
result.should == 'http://gd2.mlb.com/components/game/mlb/year_2014/month_04/day_03'
|
10
|
+
end
|
11
|
+
|
12
|
+
it 'should return a valid milb url for 2014-04-24' do
|
13
|
+
our_date = '2014-04-24'
|
14
|
+
result = Fetch.url_for_date(our_date, true)
|
15
|
+
result.should == 'http://gd2.mlb.com/components/game/milb/year_2014/month_04/day_24'
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
describe "get_game_urls" do
|
20
|
+
it 'should return list of games for April 3rd 2014' do
|
21
|
+
|
22
|
+
list_of_games = Fetch.get_game_urls('April 3rd 2014')
|
23
|
+
|
24
|
+
list_of_games.should include({:game_id => "2014_04_03_seamlb_oakmlb_1",
|
25
|
+
:game_url => "http://gd2.mlb.com/components/game/mlb/year_2014/month_04/day_03/gid_2014_04_03_seamlb_oakmlb_1/game_events.xml"})
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
describe "get_milb_schedule" do
|
30
|
+
it 'should return list of home teams for April 23rd 2014' do
|
31
|
+
list_of_games = Fetch.get_milb_schedule('April 23rd 2014')
|
32
|
+
list_of_games.should include({:home_sname=>"Tampa", :home_fname=>"Tampa Yankees", :date=>"April 23, 2014"})
|
33
|
+
end
|
34
|
+
|
35
|
+
it 'should return list of home teams for 2014-04-24' do
|
36
|
+
list_of_games = Fetch.get_milb_schedule('2014-04-24')
|
37
|
+
list_of_games.should include({:home_sname=>"Stockton", :home_fname=>"Stockton Ports", :date=>"April 24, 2014"})
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,24 @@
|
|
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
|
+
Bundler.setup
|
8
|
+
require 'pitch_fx_scraper'
|
9
|
+
|
10
|
+
|
11
|
+
RSpec.configure do |config|
|
12
|
+
config.treat_symbols_as_metadata_keys_with_true_values = true
|
13
|
+
config.run_all_when_everything_filtered = true
|
14
|
+
config.filter_run :focus
|
15
|
+
|
16
|
+
# Run specs in random order to surface order dependencies. If you find an
|
17
|
+
# order dependency and want to debug it, you can fix the order by providing
|
18
|
+
# the seed, which is printed after each run.
|
19
|
+
# --seed 1234
|
20
|
+
config.order = 'random'
|
21
|
+
end
|
22
|
+
|
23
|
+
require_relative '../lib/pitch_fx_scraper/fetch'
|
24
|
+
|
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: pitch_fx_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- David Sachitano
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-09-27 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: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.14'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.14'
|
55
|
+
description: Utilities for grabbing various data from mlb
|
56
|
+
email:
|
57
|
+
- dsachita@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- .gitignore
|
63
|
+
- .rspec
|
64
|
+
- Gemfile
|
65
|
+
- LICENSE.txt
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- lib/pitch_fx_scraper.rb
|
69
|
+
- lib/pitch_fx_scraper/fetch.rb
|
70
|
+
- lib/pitch_fx_scraper/version.rb
|
71
|
+
- pitch_fx_scraper.gemspec
|
72
|
+
- spec/fetch_spec.rb
|
73
|
+
- spec/spec_helper.rb
|
74
|
+
homepage: http://thebaseballrun.com
|
75
|
+
licenses:
|
76
|
+
- MIT
|
77
|
+
metadata: {}
|
78
|
+
post_install_message:
|
79
|
+
rdoc_options: []
|
80
|
+
require_paths:
|
81
|
+
- lib
|
82
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
83
|
+
requirements:
|
84
|
+
- - ! '>='
|
85
|
+
- !ruby/object:Gem::Version
|
86
|
+
version: '0'
|
87
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - ! '>='
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '0'
|
92
|
+
requirements: []
|
93
|
+
rubyforge_project:
|
94
|
+
rubygems_version: 2.4.1
|
95
|
+
signing_key:
|
96
|
+
specification_version: 4
|
97
|
+
summary: Initial release is focused on getting minimal schedule data.
|
98
|
+
test_files:
|
99
|
+
- spec/fetch_spec.rb
|
100
|
+
- spec/spec_helper.rb
|