NHL Stats Scraping Information

database_helper.rb

module DatabaseHelper
	require 'active_record'
	require 'pg'

	ActiveRecord::Base.establish_connection(
		adapter:  'postgresql',
		database: 'nhlstats_development',
		username: ENV['PG_USER'],
		password: ENV['PG_PASS'],
		host:     'localhost'
	)

	class Team < ActiveRecord::Base

	end

	class Player < ActiveRecord::Base

	end

	def print_all

		puts "\nTeams\n=====\n"

		Team.all.each do |t|
			puts t.inspect
		end

		puts "\n#{Team.count} records.\n"

		puts "\nPlayers\n=======\n"

		Player.all.each do |p|

			puts p.inspect
		end

		puts "\n#{Player.count} records.\n"
	end
end

scrape_players.rb

# Pulls NHL team information

# Require
require 'rubygems'
require 'json'
require 'open-uri'

# Stop loop on this game id
stopping_point = 2014020092

# Hashes to store information
names = Hash.new
numbers = Hash.new
teams = Hash.new

# Season file
season_file = open("http://live.nhl.com/GameData/SeasonSchedule-20142015.json")
season = JSON.parse season_file.read

# Loop through all games
season.each do |game|

	# Get game id
	id = game['id']

	# Limit loop
	break if id == stopping_point

	puts "Opening game: #{id}"

	# Open stats file
	stats_file = open("http://live.nhl.com/GameData/20142015/#{id}/PlayByPlay.json")
	plays = JSON.parse(stats_file.read)['data']['game']['plays']['play']

	plays.each do |play|

		# Get the player id
		player_id = play['pid']

		# Skip this play if the player has been retrieved or doesn't exist
		next if not player_id or names.has_key?(player_id)

		# Get player information
		names[player_id] = play['playername']
		numbers[player_id] = play['sweater']
		teams[player_id] = play['teamid']
	end
end

# Print out findings
names.each do |id, name|

	puts "#{id} | #{name} | #{numbers[id]} | #{teams[id]}"
end

puts "Found #{names.count} players"

scrape_teams.rb

# Pulls NHL team information

# Require
require 'rubygems'
require 'json'
require 'open-uri'

# Stop loop on this game id
stopping_point = 2014020018

# Hashes to store information
ids = Hash.new(0)
names = Hash.new

# Season file
season_file = open("http://live.nhl.com/GameData/SeasonSchedule-20142015.json")
season = JSON.parse season_file.read

# Loop through all games
season.each do |game|

	# Get game id
	id = game['id']

	# Limit loop
	break if id == stopping_point

	puts "Opening game: #{id}"

	# Get team abbreviations
	home_team_abbv = game['h']
	away_team_abbv = game['a']

	# Skip this game if both teams have already been scraped
	next if ids.has_key?(home_team_abbv) and ids.has_key?(away_team_abbv)

	# Open stats file
	stats_file = open("http://live.nhl.com/GameData/20142015/#{id}/PlayByPlay.json")
	stats = JSON.parse stats_file.read

	# Get and store team information
	ids[home_team_abbv] = stats['data']['game']['hometeamid']
	names[home_team_abbv] = stats['data']['game']['hometeamname']

	ids[away_team_abbv] = stats['data']['game']['awayteamid']
	names[away_team_abbv] = stats['data']['game']['awayteamname']
end

# Print out findings
ids.each do |abbv, id|

	puts "|#{abbv}|\t|#{names[abbv]}|\t\t|#{id}|"
end

scrape_to_database.rb

# Pulls NHL team and player information and stores it in a database

# Require
require 'rubygems'
require 'json'
require 'open-uri'

# Include database code
require_relative 'database_helper'
include DatabaseHelper

# Drop current tables
Team.delete_all
Player.delete_all

# Stop loop on this game id
stopping_point = 2014020117

# Season file
season_file = open("http://live.nhl.com/GameData/SeasonSchedule-20142015.json")
season = JSON.parse season_file.read

# Loop through all games
season.each do |game|

	# Get game id
	id = game['id']

	# Limit loop
	break if id == stopping_point

	puts "Opening game: #{id}"

	# Get team abbreviations
	home_team_abbv = game['h']
	away_team_abbv = game['a']

	# Open stats file
	stats_file = open("http://live.nhl.com/GameData/20142015/#{id}/PlayByPlay.json")
	stats = JSON.parse(stats_file.read)['data']['game']

	# Get team ids
	home_team_id = stats['hometeamid']
	away_team_id = stats['awayteamid']

	# Skip team scraping if both teams have already been scraped
	unless Team.find_by(nhl_id: home_team_id) and Team.find_by(nhl_id: away_team_id)

		# Get and store team information
		home_name = stats['hometeamname'].split ' '
		away_name = stats['awayteamname'].split ' '

		Team.create(nhl_id: home_team_id, city: home_name.first(home_name.count - 1).join(' '), name: home_name.last, abbv: home_team_abbv) unless Team.find_by(nhl_id: stats['hometeamid'])
		Team.create(nhl_id: away_team_id, city: away_name.first(away_name.count - 1).join(' '), name: away_name.last, abbv: away_team_abbv) unless Team.find_by(nhl_id: stats['awayteamid'])
	end

	# Loop through all game plays
	stats['plays']['play'].each do |play|

		# Get goalie information if possible
		if play['type'] == 'Shot'

			# Skip this goalie if already stored
			next if Player.find_by(nhl_id: play['pid2'])

			Player.create(nhl_id: play['pid2'], team_id: play['teamid'] == home_team_id ? away_team_id : home_team_id, name: play['p2name'], player_type: 'G')
		end

		# Get the player id
		player_id = play['pid']

		# Skip this play if the player has been retrieved or doesn't exist
		next if not player_id or Player.find_by(nhl_id: player_id)

		# Also skip penalties with a 3rd man (Goalie penalty)
		next if play['type'] == 'Penalty' and play['pid3']

		# Get player information
		Player.create(nhl_id: player_id, team_id: play['teamid'], name: play['playername'], sweater: play['sweater'], player_type: 'S')
	end
end

Stats.md

NHL Stats Scraping

PlayByPlay

Has detailed information on all events of the following types:

• Shots
• Hits
• Goals
• Penalties

This information includes:

• Time of the play
• Period
• Score
• Player name/number
• Secondary players involved
• Type
• Players on the ice

GCBX

###Players###

Has final type stats for all players that played in the game including:

• Jersey Number
• Goals
• Assists
• Shots
• PIMS
• Time on Ice
• Plus/Minus

###Goalies###

This includes goalies with the following information:

• Shots Against
• Saves
• Save Percentage
• Goals Against
• Time on Ice

###Teams###

Has team stat information including:

• Blocks
• Takeaways
• Power Play Percentage
• Team PIM
• Giveaways
• Faceoff Wins
• Hits

###Shots####

Includes a shot summary by period

###Penalties###

Includes a penalty summary by period

###Goals####

Includes a goal summary by period

I'm trying to use a visualization tool to show shots and other characteristics of games but I have no idea on how to use this scrubber to do that. Is there anyway to help me out here.

Thanks in advance.