pick k random files from a directory that lay within a given size range

random_file_picker.py

#!/usr/bin/env python3

"""pick k random files from a directory that lay within a given size range"""

import os
import random
import sys

if len(sys.argv) != 2:
    print(f"usage: {sys.argv[0]} dirname")
    sys.exit(-1)

K = 100
DIRNAME = sys.argv[1]
# TODO: read these in from command line
MINSIZE = 1e3  # 1kb
MAXSIZE = 1e7  # 10mb

names = os.listdir(DIRNAME)
paths = [os.path.join(DIRNAME, name) for name in names]
stats = [os.lstat(fn) for fn in paths]
ok_sized = [path for path, stat in zip(paths, stats) if MINSIZE < stat.st_size < MAXSIZE]
sample = random.choices(ok_sized, k=K)

# output paths line-by-line
for item in sample:
    print(item)