Created
October 29, 2013 06:50
-
-
Save billwanjohi/7210089 to your computer and use it in GitHub Desktop.
scrape sportstracker data
This file contains hidden or 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
require 'watir-webdriver' | |
require 'csv' | |
require 'pry' | |
# TODO: | |
# scrape specific activities (e.g. running, cycling) | |
# plot scatter | |
# fit curve | |
begin | |
b = Watir::Browser.new :phantomjs | |
b.goto "http://www.sportstracklive.com/user/#{ENV['STL_USER']}" | |
CSV.open("bests.csv", "wb") do |csv| | |
b.wait_until { b.div(class: "perf1").exists? } | |
b.divs(class: "perf1").each do |pb| | |
category, speed, quantity = | |
[pb.div(style: "float:left").text] + pb.span.text.split(' / ') | |
speed.chomp!("mph") | |
ts = category.match(/mi$/) ? quantity : category | |
weeks = ts.match(/\d+(?=w)/).to_s.to_i | |
days = ts.match(/\d+(?=d)/).to_s.to_i + weeks * 7 | |
hours = ts.match(/\d+(?=(h|hr))/).to_s.to_i + days * 24 | |
minutes = ts.match(/\d+(?=(m|min))/).to_s.to_i + hours * 60 | |
seconds = ts.match(/\d*\.?\d*+(?=(s|sec))/).to_s.to_f + minutes * 60 | |
csv << [seconds, speed] | |
end | |
end | |
ensure | |
b.close | |
end | |
# csvsort -c 1 <bests.csv |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment