def get_downloaded_list():
while True:
paths = os.listdir(TMP_FOLDER)
for i in paths:
sha256_list = []
sha256 = i.split('sha256=')[1].lower()
if sha256 == get_sha256(TMP_FOLDER + i):
if os.path.exists(get_benign_dir(sha256) + sha256):
os.remove(get_benign_dir(sha256) + sha256)
shutil.move(TMP_FOLDER + i, get_benign_dir(sha256) + sha256)
os.system('echo "' + i + '" >>' + CURRENT_DOWNLOADED)
def get_vt_list(string):
list_todo = []
path_m = get_malware_dir(string)
path_b = get_benign_dir(string)
df_b = pd.read_csv(path_b + 'reports.csv', sep=',')
df_m = pd.read_csv(path_m + 'reports.csv', sep=',')
list_m = list(df_m['sha256'])
list_b = list(df_b['sha256'])
paths = os.listdir(path_m)
for m in paths:
if len(m) == 64:
if m in list_b:
if os.path.exists(path_b + m):
continue
# os.remove(path_b+m)
shutil.move(path_m + m, path_b)
if m + '.data' in paths:
shutil.move(path_m + m + '.data', path_b)
if m + '.xml' in paths:
shutil.move(path_m + m + '.xml', path_b)
continue
elif m not in list_m:
list_todo.append(m)
return list(set(list_todo))
def write_benign(list_dict):
for dict_csv in list_dict:
try:
prex = dict_csv['sha256'][0][:3]
file_path = get_benign_dir(prex) + 'vt_report.csv'
except Exception, e:
# print str(e) + '读sha256失败'
pass
try:
df = pd.DataFrame(dict_csv, columns=columns)
if os.path.exists(file_path):
if check(file_path, dict_csv['sha256'][0]):
df.to_csv(file_path,
index=False,
sep=',',
mode='a',
header=False,
columns=columns)
else:
df.to_csv(file_path,
index=False,
sep=',',
mode='a',
columns=columns)
except Exception, e:
pass
def __name__ == '__main__':
path_list = []
for i in string:
for j in string:
for k in string:
path_list.append(get_malware_dir(i+j+k))
path_list.append(get_benign_dir(i+j+k))
GetApkData(psutil.cpu_count(), path_list)
import pandas as pd
from core.settings import get_malware_dir
from core.settings import get_benign_dir
STRPATH = '0123456789abcdef'
count_malware = 0
count_benign = 0
count_data_m = 0
count_data_b = 0
count_vt_m = 0
count_vt_b = 0
for i in list(STRPATH):
for j in list(STRPATH):
for k in list(STRPATH):
malware_file = get_malware_dir(i+j+k)
benign_file = get_benign_dir(i+j+k)
malwares = os.listdir(malware_file)
benigns = os.listdir(benign_file)
count_vt_m = count_vt_m+int(os.popen('cat '+malware_file+'vt_report.csv|wc -l').read()[:-1])
count_vt_b = count_vt_b+int(os.popen('cat '+benign_file+'vt_report.csv|wc -l').read()[:-1])
for l in malwares:
if 'xml' == l[-3:]
continue
if 'data' == l[-4:]:
count_data_m = count_data_m + 1
continue
if '.' in l:
continue
count_malware = count_malware + 1
for l in benigns:
if 'xml' == l[-3:]: