A simple python script to extract the files from a recursive zip archive.

extractlabs.py

#!/usr/bin/python

"""
A simple python script to extract the files from a recursive zip archive.

 This script is developed for a specific use of extracting student submissions from a submitted zip bundle,
 but can be modified to suit some other requirements too.

 Assumed zip structure is:
    main_archive.zip
    |
    |- student1.zip
        |- actual_files
    |- student2.zip
        |- actual_files
    |- ...

 The script extracts the actual files into individual folders named 'student1', 'student2', etc.

 Usage: $ python extractlabs.py -i <input_zip_file> -o <output_dir>

 @author Swaroop Joshi
 @version 20160910
"""

import getopt
import os
import shutil
import sys
import zipfile


def unzip(zip_file, dest_dir, ext_filter=''):
    """
    Unzips the files from a zip file and puts them in the given destination.
    Out put can be filtered by providing the file extension.
    :param zip_file: zip file to extract.
    :param dest_dir: destination folder.
    :param ext_filter: file extension. Only the files matching this extension will be extracted.
    :return: nothing
    """
    if not os.path.exists(dest_dir):
        os.makedirs(dest_dir)

    try:
        zfile = zipfile.ZipFile(zip_file)
        for filename in zfile.namelist():
            ext = os.path.splitext(os.path.basename(filename))[1]
            if (ext_filter and ext == ext_filter) or (ext_filter == ''):
                print 'Extracting {f} to {d}'.format(f=filename, d=dest_dir)
                zfile.extract(filename, dest_dir)
    except zipfile.BadZipfile:
        print 'Cannot extract {f}: Not a valid zipfile (BadZipfile Exception)'.format(f=zip_file)


def clean(targets):
    """
    Deletes the directories in the given list of targets.
    :param targets: List of targets to delete (relative or absolute paths).
    """
    for target in targets:
        if os.path.exists(target):
            print 'Removing ' + target
            shutil.rmtree(target)


def cmd_error(prog_name):
    """
    Prints out the usage instruction and exits with error status 2
    :param prog_name: Name of the script to print in the usage prompt
    """
    print 'Usage: $ python {prog} -i <input_file> -o <output_dir>'.format(prog=prog_name)
    sys.exit(2)


def read_cmd_line(argv):
    """
    Reads the command line arguments and extracts options from it.
    :param argv: Command line arguments (including the script name)
    :return: The input zip file and destination directory
    """
    opts = []
    try:
        opts, args = getopt.getopt(args=argv[1:], shortopts='hi:o:', longopts=['ifile=', 'odir='])
    except getopt.GetoptError:
        cmd_error(argv[0])

    if not opts:
        cmd_error(argv[0])

    input_file = ''
    output_dir = ''
    for opt, arg in opts:
        if opt == '-h':
            cmd_error(argv[0])
        elif opt in ['-i', '--ifile']:
            input_file = arg
        elif opt in ['-o', '--odir']:
            output_dir = arg

    if not input_file or not output_dir:
        cmd_error(argv[0])
    return input_file, output_dir


def main(argv):
    zip_file, dest_dir = read_cmd_line(argv)

    # If the dest_dir exists, remove it
    clean([dest_dir])

    # Unzip the main file first
    unzip(zip_file, dest_dir)

    # Then loop over each file in the dest_dir and unzip its contents locally
    for file in os.listdir(dest_dir):
        # Get the base name of the individual zip file without the extension
        base = os.path.splitext(os.path.basename(file))[0]
        unzip(zip_file=os.path.join(dest_dir, file), dest_dir=os.path.join(dest_dir, base))


if __name__ == "__main__":
    main(sys.argv)