A regular expression that finds N or more consecutive substrings of the same character

import re


def nchars(s, n):
    """Find a substring of the same character n or more consecutive in the string s
    """
    assert n > 0
    reg = re.compile("(.)\\1{%d,}" % (n - 1))  #If you take the comma, you get exactly n
    while True:
        m = reg.search(s)
        if not m:
            break
        yield m.group(0)
        s = s[m.end():]


print(list(nchars('a good uuu ee', 2)))
print(list(nchars('aa Ii Uuu Uu e ooo', 3)))

['Good', 'uuu', 'ee']
['Good', 'Uuuuuuu', 'ooo']

Recommended Posts