weatherhistory.py

import urllib2
import sys


if len(sys.argv) < 5:
    print "Usage: weatherhistory.py [Station Code] [Start Year] [End Year] [Month]\nie. weatherhistory.py KSMF 1980 2000 12"
    sys.exit()

airportC = sys.argv[1]
startY = sys.argv[2]
endY = sys.argv[3]
m = sys.argv[4]
# Create/open a file called wunder.txt (which will be a comma-delimited file)
f = open('wunder-data.txt', 'w')

# Iterate through year, month, and day
for y in range(int(startY), int(endY)):
  month_avg = 0
  ValidYear = True
  c = 0
  temp_avg = 0
  # Open wunderground.com url
  url = "http://www.wunderground.com/history/airport/"+airportC+"/"+str(y)+ "/" + str(m) + "/1/MonthlyHistory.html?format=1"
  page = urllib2.urlopen(url)
  for line in urllib2.urlopen(url):
    data = line.strip().split(",")
    if data[0].startswith("19") or data[0].startswith("20"):
      date = data[0]
      mean = data[2]
      # print data
      if data[2] != '':
        temp_avg += int(mean)
        if int(data[2]) < -140:
          ValidYear = False
      else:
        ValidYear = False
      c+=1
  month_avg += temp_avg / c
  #print str(y)+"-"+str(m)+" average mean: "+str(temp_avg / c)
  if ValidYear:
    print str(y)+" average mean: "+str(month_avg)
    f.write(str(y)+','+str(month_avg)+"\n")
  else:
    print "Year "+str(y)+" contained bad data and will be discarded"
  # Done getting data! Close file.
f.close()