import re
import numpy as np
from sklearn import cross_validation
from sklearn import datasets
from sklearn import svm
from sklearn.externals import joblib
from sklearn.metrics import classification_report
from sklearn import metrics
from sklearn import linear_model
from sklearn.naive_bayes import GaussianNB
from sklearn import cross_validation
from sklearn import tree
x = []
y = []
def get_len(url):
return len(url)
def get_url_count(url):
if re.search('(http://)|(https://)', url, re.IGNORECASE) :
return 1
else:
return 0
def get_evil_char(url):
return len(re.findall("[<>,\'\"/]", url, re.IGNORECASE))
def get_evil_word(url):
return len(re.findall("(alert)|(script=)(%3c)|(%3e)|(%20)|(onerror)|(onload)|(eval)|(src=)|(prompt)",url,re.IGNORECASE))
def get_last_char(url):
if re.search('/$', url, re.IGNORECASE) :
return 1
else:
return 0
def get_feature(url):
return [get_len(url),get_url_count(url),get_evil_char(url),get_evil_word(url),get_last_char(url)]
def etl(filename,data,isxss):
with open(filename) as f:
for line in f:
f1=get_len(line)
f2=get_url_count(line)
f3=get_evil_char(line)
f4=get_evil_word(line)
data.append([f1,f2,f3,f4])
if isxss:
y.append(1)
else:
y.append(0)
return data
etl('../data/xss-200000.txt',x,1)
etl('../data/good-xss-200000.txt',x,0)
clf = tree.DecisionTreeClassifier()
clf2 = svm.SVC(kernel='linear', C=1)
clf3 = linear_model.LogisticRegression(C=1e5)
clf4 = GaussianNB()
for name,clf in {"decision tree":clf, "svm train long time":clf2, "LR":clf3, "bayes":clf4}.iteritems():
#for name,clf in {"decision tree":clf, "LR":clf3, "bayes":clf4}.iteritems():
print "model:", name
score=cross_validation.cross_val_score(clf, x, y, n_jobs=-1, cv=5)
print score
print np.mean(score)
