import urllib
import urllib2
import csv

url = 'http://www.bts.gov/airline_employment/src/datadisp_csv.xml?o=NAME+ASC'
values = {'month' : '09',
           'year' : '2008'}

data = urllib.urlencode(values)
req = urllib2.Request(url, data)
response = urllib2.urlopen(req)

the_page = response.read()

f = open('test2.csv', 'r+')
f.write(the_page)

raw = open('/home/abhi/Dropbox/hobby/govdata/test2.csv', "rb")

clean = open('/home/abhi/Dropbox/hobby/govdata/clean.csv', "w")

#write header
clean.write('Group,Month,Year,Carrier Name,Full Time,Part Time,Total,Blank\n')

group = "Major"
year = "2008"
month = "09"


for line in raw:

      if line.find(',') == 2:

          strline = str(line)
          strline = strline.replace('  ,,,','') 
          
          if strline.find('TOTAL') < 0:
              thisline = group + ',' + month + ',' + year + ','+ strline 
              clean.write(thisline)

      elif line.find(',') == 10: 
          group = "National"
      elif line.find(',') == 16: 
          group = "Large Regional"
      elif line.find(',') == 17 & line.find('G') > 1:
          group = "Medium Regional"
      else :
          print ""

cleanread = open('/home/abhi/Dropbox/hobby/govdata/clean.csv', "rb")

for line in cleanread:
    print line