using lambda with python to transform dataset

spark.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re

dataset = sc.textFile("file:///home/cloudera/massa_de_exemplo_wol.txt")
categories = []
regex = r"(\/[^, z]*\.[a-z]\w)+"
    
result = dataset.map(lambda line: re.search(regex, line).group(0).split('/')[1])
# print result

for category in result:
  if not category in categories:
    categories.append(category)

# print categories