finddup.py

import hashlib, os, sqlite3, sys

con = sqlite3.connect("hash.db")
cur = con.cursor()
cur.execute("delete from files")

for root, dirs, files in os.walk(sys.argv[1]):
    for file in files:
        filename = root + "/" + file 
        with open(filename, 'br') as f:
            size = os.stat(filename).st_size
            if size > 4194304:
                hash = hashlib.sha256(f.read(8192)).hexdigest()
                cur.execute(f"""insert into files values ("{hash}", {size}, "{root}", "{file}")""")

con.commit()
con.close()