Splits a folder into zip files of a certain MB size or lower. If a file is larger than the limit, then it will have its own zip file.

split.py

#!/usr/bin/env python3

# Copyright Nikunj Chawla 2023

import sys
import os
import re
from zipfile import ZipFile, ZIP_DEFLATED
from math import ceil

zipfile_regex = re.compile(r"^zip_\d+\.zip$")

if len(sys.argv) != 3:
    print("Usage: python split.py [pathToDir] [splitSizeMb]")
    sys.exit(1)

dir_path = sys.argv[1]

try:
    split_size = int(sys.argv[2]) * 1024 * 1024
except ValueError:
    print("Second argument must be integer")
    sys.exit(1)

num_digits = 0

cur_file_size = 0
cur_files = []
zip_file_counter = 0

total_size = 0

def zip_files() -> None:
    global zip_file_counter
    global cur_files
    
    with ZipFile(os.path.join(dir_path, f"zip_{str(zip_file_counter).zfill(num_digits)}.zip"), "w") as zipf:
        while cur_files:
            zipf.write(cur_files.pop(), compress_type = ZIP_DEFLATED)
    print(f"Zip {str(zip_file_counter).zfill(num_digits)} completed")
    zip_file_counter += 1

for root, _, files in os.walk(dir_path):
    for file in files:
        total_size += os.path.getsize(os.path.join(root, file))

splits = max(0, ceil(total_size / split_size) - 1)
num_digits = len(str(splits))

for root, _, files in os.walk(dir_path):
    for file in files:
        if zipfile_regex.match(file):
            continue
        
        full_path = os.path.join(root, file)
        file_size = os.path.getsize(full_path)
        if cur_file_size + file_size <= split_size:
            cur_file_size += file_size
        else:
            zip_files()
            cur_file_size = file_size
        cur_files.append(full_path)

if cur_files:
    zip_files()