def tokenize(f):

  # Skip headers
  data = f.read()
  eoh = data.find('\n\n')
  data = data[eoh+1:]
  data = data.lower()

  # More opportunities here as well if this turns out to be a good idea
  for char in ['\n','.','!',"'",':','?','@','=',',']:
    data = data.replace(char,' ')

  data = data.replace('><','> <')
  tokens = data.split()
  tokens = [t for t in tokens if len(t) > 0 and t not in stopwords]

  return tokens