gistfile1.txt

from __future__ import print_function
# import os
import json
# import sys
from pathlib import Path

# Why did you not use Glob on Path???
import glob

def findfiles():

    # HARDCODED MAGIC STRING
    # WHERE DID THIS MAGIC STRING COME FROM
    logpath = './json-data/json-formatted/'
    logs = []
    hashes = []
    hashset = {}

    # Why not use pathlib???
    logfiles = [log for log in glob.glob(logpath + '**/*.json', recursive=True)]

    for log in logfiles:
        with open(log) as logfile:

            # X?????
            # WHAT KIND OF VARIABLE NAME IS THAT???
            # WHAT IS THIS C? GO?
            x = json.load(logfile)

            #  WHY DO WE GRAB THE FIRST ELEMET?
            # WhAT IF X is Len 0
            # WHATS UP WITH THIS MAGIC cowrie String?????
            if x[0]['eventid'] == 'cowrie.session.file_download':
                outfile = x['outfile']
                # THIS MAKES ME UNCOMFORTABLE
                print_function(outfile)
                logs.append(outfile)
    # WHAT IS A VARIABLE FOR ANTS:???
    for i in logs:

        # AGAIN WITH THE XXXXXXX??
        x = Path(i).stem
        hashes.append(x)

    # This is just to enforce uniquenesss????
    hashset = list(set(hashes))

    # filehandle.......ugh
    with open('hashes.txt', 'w') as filehandle:
        # WHAT ARE YOU DOING
        # HASH IS KEYWORD
        # ITS HIGHLIGHTED
        # STOP USING HASH AS A TEMP VARIABLE
        filehandle.writelines("%s\n" % hash for hash in hashset)


# WHAT THE HECK IS VT
# Virgiina Tech resource
# Sig ->
def vtfiles_resource_sig():
    # A ./ in a MAGIC STRING!!!!!!!!!!!!!
    vt_report_path = './vt/'
    files = []


    # AGAIN WITH THE GLOBBING
    allfiles = [f for f in glob.glob(vt_report_path + '**/*.json', recursive=True)]

    # WHAT ARE YOU DOING, STOP USING KEYWORDS AS TEMP VARIABLES
    # PEOPLE COULD GET HURT
    for file in allfiles:
        with open(file) as f:

            # What is this file isn't VALID JSON???
            j = json.load(f)

            # WHAT is J is len(0)???
            # This really depends on the structure of theese files
            # Why check again '1' and 1,
            # why not convert to int, then compare????
            if j[0]['response_code'] == '1' or j[0]['response_code'] == 1:
                # This is reaching twice into a datastructure,
                # That we don't know will match this
                resources = j[0]['resource']
                files.append(resources)

    with open('resources.txt', 'w') as filehandle:
        filehandle.writelines("%s\n" % resource for resource in files)


def compare_res_sig_to_hash():
    matches = {}
    # A, B??!?!?
    # VARIABLE SHADOWING
    a = open('resources.txt', 'r').read().splitlines()
    a = set(a)
    b = open('hashes.txt', 'r').read().splitlines()
    b = set(b)
    matches = set(a).intersection(b)

    with open('matches.txt', 'w') as filehandle:
        filehandle.writelines("%s\n" % match for match in matches)

if __name__ == '__main__':
    findfiles()
    # vtfiles_resource_sig()
    # compare_res_sig_to_hash()