You should look into itertools.groupby:
from collections import defaultdict
from itertools import groupby
def class_chars(chrs):
if 'N' in chrs:
return 'unknown'
elif chrs[0] == chrs[1]:
return 'match'
else:
return 'not_match'
s1 = 'aaaaaaaaaaN123bbbbbbbbbbQccc'
s2 = 'aaaaaaaaaaN456bbbbbbbbbbPccc'
n = 0
consec_matches = []
chars = defaultdict(int)
for k, group in groupby(zip(s1, s2), class_chars):
elems = len(list(group))
chars[k] += elems
if k == 'match':
consec_matches.append((n, n+elems-1))
n += elems
print chars
print consec_matches
print [x for x in consec_matches if x[1]-x[0] >= 9]
Output:
defaultdict(<type 'int'>, {'not_match': 4, 'unknown': 1, 'match': 23})
[(0, 9), (14, 23), (25, 27)]
[(0, 9), (14, 23)]