temp.py

# # import numpy as np
# # data=open('8496.txt').read().split('\n')
# # # print(data[:100])
# # mem_val=[]
# # for i in range(0,len(data)):
# #     mem_val.append((data[i].split(' '))[1:9])
# #
# # mem_val=np.array(mem_val)
# # print(mem_val.shape)
# #
#
#
#
#
#
# # def Yara_Signature_Dataset():
# #
# #     rootdir = './scans/yarascan/'
# #     file_name = []
# #     sub_dir = []
# #     for subdir, dirs, files in os.walk(rootdir):
# #         for file in files:
# #             file_name.append(file)
# #             sub_dir.append(subdir)
# #     dataset_benign=[]
# #     dataset_malwares=[]
# #     y=[]
# #     for z in range(3, len(file_name)-1):
# #         if sub_dir[z] == './scans/yarascan/Benign Samples':
# #             f = open(sub_dir[z] + '/' + file_name[z], "r").read()
# #             print(file_name[z])
# #             data=(f.split('\n'))
# #             rule_indexes=[]
# #             for i in range(0,len(data)):
# #                 if data[i].__contains__('Rule:'):
# #                     rule_indexes.append(i)
# #                 else:
# #                     continue
# #             benign_hex=[]
# #             for i in range(0,len(rule_indexes)-1):
# #                 benign_values=[]
# #                 y.append(0)
# #                 for j in range(rule_indexes[i]+2,rule_indexes[i+1]):
# #                     mem_values=(data[j].split(' '))
# #                     mem_values=[(int(i,16)) for i in mem_values[2:len(mem_values)-3]]
# #                     # print(mem_values)
# #                     benign_values.append(mem_values)
# #                 benign_hex.append(benign_values)
# #             benign_hex=np.array(benign_hex)
# #             # print(benign_hex)
# #         else:
# #             f = open(sub_dir[z] + '/' + file_name[z], "r").read()
# #             print(file_name[z])
# #             for i in mal_name_id:
# #                 if file_name[z].split('_')[0]==i[0]:
# #                     print(i)
# #                     break
# #                 else:
# #                     continue
# #             data = (f.split('\n'))
# #             rule_indexes = []
# #             for i in range(0, len(data)):
# #                 if data[i].__contains__('Rule:'):
# #                     print(data[i+1].split(' ')[4])
# #                     rule_indexes.append(i)
# #                 else:
# #                     continue
# #             # mal_hex = []
# #             # for i in range(0, len(rule_indexes) - 1):
# #             #     mal_values = []
# #             #     y.append(1)
# #             #     for j in range(rule_indexes[i] + 2, rule_indexes[i + 1]):
# #             #         mem_values = (data[j].split(' '))
# #             #         mem_values = [(int(i, 16)) for i in mem_values[2:len(mem_values) - 3]]
# #             #         # print(mem_values)
# #             #         mal_values.append(mem_values)
# #             #     mal_hex.append(benign_values)
# #             # mal_hex = np.array(mal_hex)
# #             # print(mal_hex)
# #
# #
# # Yara_Signature_Dataset()
#
#
#
#
# def malfind_dataset():
#     rootdir = './scans/malfind/'
#     file_name = []
#     sub_dir = []
#     for subdir, dirs, files in os.walk(rootdir):
#         for file in files:
#             file_name.append(file)
#             sub_dir.append(subdir)
#     # dataset_benign=[]
#     # dataset_malwares=[]
#     y=[]
#     for z in range(0, len(file_name)):
#         if sub_dir[z] == './scans/malfind/Benign Samples':
#             f = open(sub_dir[z] + '/' + file_name[z], "r").read()
#             print(file_name[z])
#             data=(f.split('\n'))
#             rule_indexes=[]
#             for i in range(0,len(data)):
#                 if data[i].__contains__('Rule:'):
#                     rule_indexes.append(i)
#                 else:
#                     continue
#         #     benign_hex=[]
#         #     for i in range(0,len(rule_indexes)-1):
#         #         benign_values=[]
#         #         y.append(0)
#         #         for j in range(rule_indexes[i]+2,rule_indexes[i+1]):
#         #             mem_values=(data[j].split(' '))
#         #             mem_values=[(int(i,16)) for i in mem_values[2:len(mem_values)-3]]
#         #             # print(mem_values)
#         #             benign_values.append(mem_values)
#         #         benign_hex.append(benign_values)
#         #     benign_hex=np.array(benign_hex)
#         #     # print(benign_hex)
#         else:
#             f = open(sub_dir[z] + '/' + file_name[z], "r").read()
#             print(file_name[z])
#             for i in mal_name_id:
#                 if file_name[z].split('_')[0]==i[0]:
#                     print(i)
#                     break
#                 else:
#                     continue
#             data = (f.split('\n'))
#             rule_indexes = []
#         #     for i in range(0, len(data)):
#         #         if data[i].__contains__('Rule:'):
#         #             print(data[i+1].split(' ')[4])
#         #             rule_indexes.append(i)
#         #         else:
#         #             continue
#         #     mal_hex = []
#         #     for i in range(0, len(rule_indexes) - 1):
#         #         mal_values = []
#         #         y.append(1)
#         #         for j in range(rule_indexes[i] + 2, rule_indexes[i + 1]):
#         #             mem_values = (data[j].split(' '))
#         #             mem_values = [(int(i, 16)) for i in mem_values[2:len(mem_values) - 3]]
#         #             # print(mem_values)
#         #             mal_values.append(mem_values)
#         #         mal_hex.append(benign_values)
#         #     mal_hex = np.array(mal_hex)
#         #     print(mal_hex)
#
#
# malfind_dataset()


import os
print(os.listdir())