Sometimes I extract a zip or rar archive and don't care to delete one or the other, so now both the archive and its extracted contents take up disk space. This script hunts for such cases and offers to delete the extracted files. It could be modified to offer to delete the archive instead, too.

delete_redundant_extracted.py

# encoding=utf8
import os, zipfile, rarfile, tarfile, shutil

# avoid encoding problems
import sys
reload(sys)
sys.setdefaultencoding('utf8')


def remove_file_or_tree(p):
    if os.path.exists(p):
        if os.path.isdir(p):
            shutil.rmtree(p)
        else:
            os.remove(p)


def get_paths_inside_archive(archive_path):
    if archive_path.endswith(".zip"):
        try:
            return zipfile.ZipFile(archive_path).namelist()
        except zipfile.BadZipfile:
            print "bad file: ", archive_path

    elif archive_path.endswith(".rar"):
        try:
            return rarfile.RarFile(archive_path).namelist()
        except rarfile.NotRarFile:
            print "bad file: ", archive_path
        except rarfile.NeedFirstVolume:
            pass

    elif archive_path.endswith(".tar.gz"):
        try:
            return tarfile.open(archive_path, 'r:gz').getnames()
        except tarfile.TarError:
            print "bad file: ", archive_path

    return []


def targz_aware_splitext(path):
    if path.endswith(".tar.gz"):
        return path[:-len(".tar.gz")], path[-len(".tar.gz"):]
    else:
        return os.path.splitext(path)


def delete_redundant_extracted_files(root_dir_of_search):

    for dir_path, subdir_list, file_list in os.walk(root_dir_of_search):
        for filename in file_list:

            archive_basename, ext = targz_aware_splitext(filename)
            if ext not in (".zip", ".rar", ".tar.gz"):
                continue

            filepath = os.path.join(dir_path, filename)
            files_in_archive = get_paths_inside_archive(filepath)

            redundant_extracted_paths = []
            for filename_in_archive in files_in_archive:
                extracted_candidate1 = os.path.join(dir_path, filename_in_archive)
                extracted_candidate2 = os.path.join(dir_path, archive_basename, filename_in_archive)

                for candidate in (extracted_candidate1, extracted_candidate2):
                    if os.path.exists(candidate):
                        redundant_extracted_paths.append(candidate)

            if any(os.path.getsize(p) > 50*1024*1024 for p in redundant_extracted_paths):
                if raw_input('Delete all redundant files extracted from ' + filepath + '? (y/n) ') == "y":
                    for extracted_path in redundant_extracted_paths:
                        remove_file_or_tree(extracted_path)

                    extracted_root = os.path.join(dir_path, archive_basename)
                    remove_file_or_tree(extracted_root)

                print "\n"