classifyNotVirus.py

import os
import sys
import shutil
import re
import collections
import pprint

walk_dir = sys.argv[1]

print('walk_dir = ' + walk_dir)

# If your current working directory may change during script execution, it's recommended to
# immediately convert program arguments to an absolute path. Then the variable root below will
# be an absolute path as well. Example:
walk_dir = os.path.abspath(walk_dir)
print('walk_dir (absolute) = ' + os.path.abspath(walk_dir))


cnt = 0

for root, subdirs, files in os.walk(walk_dir):
    list_file_path = os.path.join(root, '')


    filename = "virustotal.txt"

    if filename in files:
        file_path = os.path.join(root, filename)

        print('\n+++++++++++++New File Full path: %s' % (file_path))

        with open(file_path) as f:
            words = re.findall(r"\bnot-a-virus\b", f.read().lower())

            if words:
                print "==================================> NOT A VIRUS with words:"
                print words
                cnt+= 1
                shutil.move(root, "/home/tarun/Documents/Classified/not-a-virus")
            #break;

print cnt #print all identified keywords