HackerRank - "Detect HTML Attributes"

import re

n = int(input())
txt = ''
for _ in range(n):
str = input()
txt = txt + str

dict = {}
all = re.findall('<[^/][^<>]*>', txt)
for i in range(len(all)):
segs = re.split(' ', all[i][1:-1])
if not segs[0] in dict:
dict[segs[0]] = set([])
if (len(segs) > 1):
tags = re.findall("\s[a-z]+=", all[i][1:-1])
for j in range(len(tags)):
dict[segs[0]].add(tags[j][1:-1])

sortedKeys = list(dict.keys())
sortedKeys.sort()
for k in sortedKeys:
print(k + ':', end="")
tags = list(dict[k])
tags.sort()
print (','.join(tags))