diff --git a/.idea/Gencoding.iml b/.idea/Gencoding.iml
index d9ff559..7ba4311 100644
--- a/.idea/Gencoding.iml
+++ b/.idea/Gencoding.iml
@@ -4,7 +4,7 @@
-
+
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
index 7ba73c2..44f3bc1 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -1,4 +1,7 @@
-
+
+
+
+
\ No newline at end of file
diff --git a/raw-feature-extractor/print_test.py b/raw-feature-extractor/print_test.py
index 2cca783..13df20f 100644
--- a/raw-feature-extractor/print_test.py
+++ b/raw-feature-extractor/print_test.py
@@ -21,19 +21,15 @@ import pickle
# sub_10F20 308 反编译代码有字符串,但是这个特征提取里没有字符串 constant,可能是间接引用的,不识别。看了下所有函数的特征,几乎都没有字符串常量,可能都是写在别的地方然后引用的。
# sub_166C4 393
-
-
-if __name__ == '__main__':
+def main_op(file_path, jsonl_file):
done_index = 0
- file_name_list = os.listdir('../A2C/')
- res_file = "../sample.jsonl"
- sample_file = open(res_file, mode='a')
+ file_name_list = os.listdir(file_path)
+ sample_file = open(jsonl_file, mode='a')
for file_name in file_name_list:
print file_name
- file_path = '../A2C/' + file_name
- testpath = '../store/' + file_name + '.ida'
- if os.path.exists(testpath) and os.path.splitext(file_path)[-1].lower() == '.exe':
- fr = open(testpath, 'r')
+ file_path_temp = file_path + file_name
+ if os.path.exists(file_path_temp) :
+ fr = open(file_path_temp, 'r')
data1 = pickle.load(fr) # 一个二进制文件的acfgs
# funtion num
function_number = len(data1.raw_graph_list)
@@ -109,3 +105,8 @@ if __name__ == '__main__':
print "删除文件" + file_path
os.remove(file_path)
sample_file.close()
+
+if __name__ == '__main__':
+ file_path = "../train_malware_result/"
+ jsonl_path = "../jsonl_res/malware_result.jsonl"
+ main_op(file_path, jsonl_path)
diff --git a/raw-feature-extractor/raw_graphs.py b/raw-feature-extractor/raw_graphs.py
index eb40c2e..0e61b78 100755
--- a/raw-feature-extractor/raw_graphs.py
+++ b/raw-feature-extractor/raw_graphs.py
@@ -1,7 +1,7 @@
import itertools
import sys
-sys.path.insert(1, 'C:/Python27/Lib/site-packages')
+
import networkx as nx
# import numpy as np
from subprocess import Popen, PIPE