-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtestClass.py
162 lines (134 loc) · 3.56 KB
/
testClass.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
import random
import getFeatures
from sys import argv
from bs4 import BeautifulSoup
import csv
def cleanString(dirtyString):
output = "";
for ch in dirtyString:
if ord(ch)< 127:
output += ch
return output;
print "Testing"
csvFile = open("data/small.csv","a")
csvWriter= csv.writer(csvFile)
passedScriptsFile = open("passedScriptsFile.txt","w")
failedScriptsFile = open("failedScriptsFile.txt","w")
f= open("ADD-3",'r');
#f= open("SUPERBAD1.txt","r")
txt = f.read()
d=0
#jsFile = open("malJS.js","w")
#print str(len(f.read().split("\n"))
allVal=[]
totalScripts = len(txt.split("###############"))
#totalScripts = 100
tempList= []
tempList.append(totalScripts-1)
tempList.append(28)
allVal.append(tempList)
invalid =0
valid =0
allJs = txt.split("###############")
for item in allJs[:len(allJs)-1]:
#for item in allJs[:len(allJs)-1]:
#item = random.choice(allJs)
currVal=[]
#print str(len(item))
#print
#if d >=int(start) and d< int(end):
if d>=0:
#print item
print
soup = BeautifulSoup(item)
script = soup.find("script")
ret ={}
#condition for top level script
if script is not None:
if script.parent.name == "head" :
actItem = script.text
ret = getFeatures.getFeatures(cleanString(actItem))
else:
ret = getFeatures.getFeatures(cleanString(item))
else:
ret = getFeatures.getFeatures(cleanString(item))
print ".....................................................SCRIPT COUNT" + str(d+1)
#skip this entry if could not be parsed
if len(ret.keys())!=0:
valid+=1
for key in ret.keys():
currVal.append(ret[key])
#print "current key is " + str(key) + " and value is " + str(ret[key])
#append a 1 for malicious
currVal.append("1")
#print "No of keys is " + str(len(ret.keys()))
if(currVal not in allVal and "-1" not in currVal):
#allVal.append(currVal)
csvWriter.writerow(currVal)
#passedScriptsFile.write(cleanString(item)+ "\n")
#passedScriptsFile.write("##########+\n")
else:
#failedScriptsFile.write(cleanString(item)+ "\n")
#failedScriptsFile.write("##########+\n")
print cleanString(item)
#item = script.text
#getFeatures.getFeatures(item)
#jsFile.write(it
else:
invalid+=1;
#print
d+=1
passedScriptsFile.close()
failedScriptsFile.close()
"""
f.close()
f= open("all_good_scripts_1.txt","r")
txt = f.read()
d=0
for item in txt.split("##########"):
currVal=[]
#print str(len(item))
#print
#if d >=int(start) and d< int(end):
if d<1000:
#print item
print
soup = BeautifulSoup(item)
script = soup.find("script")
ret ={}
#condition for top level script
if script is not None:
if script.parent.name == "head" :
actItem = script.text
ret = getFeatures.getFeatures(actItem)
else:
ret = getFeatures.getFeatures(item)
else:
ret = getFeatures.getFeatures(item)
print ".....................................................SCRIPT COUNT" + str(d+1)
#skip this entry if could not be parsed
if len(ret.keys())!=0:
valid+=1
for key in ret.keys():
currVal.append(ret[key])
print "current key is " + str(key) + " and value is " + str(ret[key])
#append a 1 for malicious
currVal.append("0")
print "No of keys is " + str(len(ret.keys()))
allVal.append(currVal)
#item = script.text
#getFeatures.getFeatures(item)
#jsFile.write(it
else:
invalid+=1;
#print
d+=1
"""
print "TOtal no of js" + str(totalScripts)
print "No of failures" + str(invalid)
print "success " + str(valid)
#csvWriter.writerows(allVal);
#print str(len(txt.split("###############")))
#jsFile.close()
f.close()
csvFile.close()