Clean a web crawl

import hashlib

def words(text):
    # Lowercase and drop punctuation, so formatting changes do not count.
    return "".join(c.lower() if c.isalnum() else " " for c in text).split()

def shingles(text, n=5):
    w = words(text)
    return {" ".join(w[i:i + n]) for i in range(len(w) - n + 1)}

def minhash(shingle_set, k=112):
    # Hash function i scores each shingle by the MD5 of "i:shingle".
    # The signature keeps the smallest score for each of the k functions.
    return [min(int(hashlib.md5(f"{i}:{s}".encode()).hexdigest()[:8], 16)
                for s in shingle_set) for i in range(k)]

original = ("Harbor City recorded 112 millimeters of rain on Saturday, the wettest "
            "single day since the city's weather station opened in 1952. Water "
            "covered parts of Front Street and the river path by mid-afternoon.")
repost = ("Storm brings record rain. Harbor City recorded 112 millimeters of rain "
          "this Saturday, the wettest single day since the city's weather station "
          "opened in 1952. Water covered parts of Front Street and the river path "
          "by mid-afternoon. Originally published by Harbor Daily.")
other = ("Volunteers cleared mud from Front Street on Sunday after the rain, the "
         "heaviest the city has measured in a single day since 1952.")

a = shingles(original)
sig_a = minhash(a)
for name, text in [("repost", repost), ("other story", other)]:
    b = shingles(text)
    exact = len(a & b) / len(a | b)
    sig_b = minhash(b)
    estimate = sum(x == y for x, y in zip(sig_a, sig_b)) / len(sig_a)
    print(f"{name:11}  exact {exact:.2f}  MinHash estimate {estimate:.2f}")

repost       exact 0.58  MinHash estimate 0.51
other story  exact 0.00  MinHash estimate 0.00