Scrape TimeOnIce.com

play.py

import urllib2
from bs4 import BeautifulSoup
import datetime

start = datetime.datetime.now()

teams = ["MIN", "MTL", "N.J", "NSH", "NYI", "NYR", 
		 "OTT", "PHI", "PHX", "PIT", "S.J", "STL", "T.B", "TOR", "VAN", "WSH"]
		 
seasons = ["0809", "0910", "1011"]

tied = {'tied': 'tied', 'close': ''}

for t in teams:
	for s in seasons:
		for i in tied:
			url = "http://timeonice.com/mplayershots"+s+""+tied[i]+".php?team="+t+"&first=20001&last=21230&hv=0"


			print "opening: "+url
			soup = BeautifulSoup(urllib2.urlopen(url).read())		

			print "analyzing"
			newline = None

			rows = soup.table.findAll('tr')[-1]
			stats = rows.find_all('td')
			
			newline = [s, t, i, stats[2].text, stats[3].text, stats[4].text, stats[5].text, 
						stats[7].text, stats[8].text, stats[10].text, stats[11].text]
						
			newline = ",".join(str(x) for x in newline)
			
			file = open('stats.csv','a')
			file.write(newline + "\n")
			file.close()

print "done"

end = datetime.datetime.now()
print end - start