Python script to list the packages contained in a folder full of jar files (e.g. for scanning jar files in WEB-INF/lib)

jar-list-packages.py

#!/usr/bin/python
from __future__ import print_function

import string
import os
import sys
import re
import argparse
from subprocess import Popen, PIPE

parser = argparse.ArgumentParser(
    description = "List packages contained in jar files")

parser.add_argument('-d', '--dir', required=False, nargs=1)
parser.add_argument('-v', '--verbose', required=False, action="store_true")

args = parser.parse_args()

jar_folder = (args.dir[0] if args.dir else None) or os.getcwd()

def verbose(s):
    if args.verbose:
        print(s)

verbose('Current folder: ' + str(jar_folder))

packages = set()

files = [f for f in os.listdir(jar_folder) 
         if os.path.isfile(os.path.normpath(jar_folder) + os.sep + f) 
         and f[-3:] == 'jar']

verbose(str(files))

for f in files:
    verbose('File: ' + f)
    s = Popen(['jar', 'tf', f], stdout=PIPE, cwd=jar_folder).stdout.read()
    for line in s.split('\n'):
        if line.find('META-INF') == -1:
            verbose(line)
            last_slash = line.rfind('/')
            if last_slash > 0:
                packages.add(line[:last_slash].replace('/', '.'))

verbose('Packages:')
                
for p in sorted(packages):
    print(p)