Last active
August 29, 2015 14:20
-
-
Save willpearse/e1d5a92c03388012eb77 to your computer and use it in GitHub Desktop.
Scraping player minor penalties from NHL
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Headers | |
require 'open-uri' | |
require 'nokogiri' | |
require 'set' | |
#Get all the penalty stats | |
results = [] | |
(2011..2014).to_a.each do |year| | |
(0..30).to_a.map{|x| x * 40 + 1}.each do |player_count| | |
page = Nokogiri::HTML(open("http://espn.go.com/nhl/statistics/player/_/stat/minor-penalties/sort/minorPenalties/year/#{year}/seasontype/2/count/#{player_count}")) | |
page.css("tr").each do |entry| | |
unless entry.text == "RKPLAYERTEAMPIMMINORHKTRRGHHLDINTSLHHSCCHLDSTGLINT" | |
temp = entry.children.map {|x| x.text} | |
temp.push(year) | |
results.push(temp) | |
end | |
end | |
end | |
end | |
#Get all the images | |
unique_players = Set.new(results.map{|x| x[1]}) | |
unique_players.each do |player| | |
player = player[/[a-zA-Z ]*/] | |
player = player.sub(" ", "-") | |
File.open("#{player}.png", "w") do |handle| | |
handle << open("http://assets1.sportsnet.ca/wp-content/uploads/players/nhl/#{player[0]}/#{player}.png") | |
end | |
end | |
#Write out the player statistics | |
File.open("fred_hockey.txt", "w") do |handle| | |
results.each do |line| | |
handle << "#{line.join("\t")}\n" | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment