def process_test_url(url, output_dest):
feature = []
url = url.strip()
if url != '':
print 'working on: ' + url #showoff
ret_dict = urlfeature.feature_extract(url)
feature.append([url, ret_dict])
resultwriter(feature, output_dest)
def process_test_url(url,output_dest): # i think this takes a single url to extract feature, this is used in gui.py file only
feature=[]
url=url.strip()
if url!='':
print ('working on: '+url) #showoff
ret_dict=urlfeature.feature_extract(url)
feature.append([url,ret_dict]);
resultwriter(feature,output_dest)
def process_test_list(file_dest, output_dest):
feature = []
with open(file_dest) as file:
for line in file:
url = line.strip()
if url != '':
print 'working on: ' + url #showoff
ret_dict = urlfeature.feature_extract(url)
feature.append([url, ret_dict])
resultwriter(feature, output_dest)
def process_test_list(file_dest,output_dest): # i think this takes whole file of urls without given malicious to extract their feature and doest not provide malicious column like this will take query.txt
feature=[]
with open(file_dest) as file:
for line in file:
url=line.strip()
if url!='':
print ('working on: '+url) #showoff
ret_dict=urlfeature.feature_extract(url)
feature.append([url,ret_dict]);
resultwriter(feature,output_dest)
def process_URL_list(file_dest,output_dest):# i think this takes whole file of urls with given malicious to extract their feature and provide malicious column also like this will take url.txt
feature=[]
with open(file_dest) as file:
for line in file:
url=line.split(',')[0].strip()
malicious_bool=line.split(',')[1].strip()
if url!='':
print ('working on: '+url) #showoff
ret_dict=urlfeature.feature_extract(url)
ret_dict['malicious']=malicious_bool
feature.append([url,ret_dict]);
resultwriter(feature,output_dest)
def process_URL_list(file_dest, output_dest):
feature = []
with open(file_dest) as file:
for line in file:
url = line.split(',')[0].strip()
malicious_bool = line.split(',')[1].strip()
if url != '':
print('working on: ', url) #showoff
ret_dict = urlfeature.feature_extract(url)
ret_dict['malicious'] = malicious_bool
feature.append([url, ret_dict])
resultwriter(feature, output_dest)
def submit():
if (request.method == 'POST'):
features = []
data = request.get_json()
print(data)
sms = data['msg']
#Check for URL in msg
url = ''
for w in sms.split(' '):
if (w.startswith('https:') or w.startswith('http:')
or w.startswith('www')):
url = w
if url != '':
url = str(url)
features.append(urlfeature.feature_extract(url))
df = pd.DataFrame(features)
ans_np = list(rf_model.predict(df[train_cols]))
# print 'URL is: ',url
# print '\n ANS is: ',ans[0]
ans = int(ans_np[0])
if (ans == 1):
features.append({
'ans': ans,
'flash': 'Site entered is SUSPICIOUS',
'url': url
})
elif (ans == 0):
features.append({
'ans': ans,
'flash': 'Site entered is SAFE',
'url': url
})
else:
features.append({
'ans': ans,
'flash': 'Site entered is MALICIOUS',
'url': url
})
return {'features': features}
else:
error = 'Please enter a valid URL'
return {'error': error}
def process_URL_list(file_dest, output_dest):
feature = []
with open(file_dest) as file:
for line in file:
##对每一行内容进行划分为链接和标签
content_list = line.split(",")
##url链接
url = content_list[0].strip()
##标签
malicious_bool = content_list[1].strip()
if url:
print 'working on: ' + url
##url特征提取
ret_dict = urlfeature.feature_extract(url)
###输出恶意代码类型
ret_dict['malicious'] = malicious_bool
feature.append([url, ret_dict])
file.close()
resultwriter(feature, output_dest)
