def predict_url(url):
try:
if isinstance(url, str):
features = mod_feature_extraction.extract_features_from_URL(url, "PREDICT", True)
x_pred = pd.DataFrame(features)
else:
x_pred = url
x_pred = transform_data(x_pred)
random_forest = load_model()
y_pred = random_forest.predict(x_pred)
return y_pred.tolist()
except Exception as e:
exc_type, exc_obj, tb = sys.exc_info()
f = tb.tb_frame
lineno = tb.tb_lineno
filename = f.f_code.co_filename
linecache.checkcache(filename)
line = linecache.getline(filename, lineno, f.f_globals)
print('EXCEPTION IN ({}, LINE {} "{}"): {}'.format(filename, lineno, line.strip(), exc_obj))
log(action_logging_enum=WARNING, logging_text=str(e))
log(action_logging_enum=WARNING, logging_text=str(e.__traceback__))
return None
def predict_url(url):
try:
features = mod_feature_extraction.extract_features_from_URL(
url, "PREDICT", True)
x_pred = pd.DataFrame(features)
x_pred = x_pred.drop(["Label", "ID", "URL"], axis=1)
y_pred = adaptive_boosting_pre_loaded.predict(x_pred)
result = "NO RESULT"
int_result = 0
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
except Exception as e:
exc_type, exc_obj, tb = sys.exc_info()
f = tb.tb_frame
lineno = tb.tb_lineno
filename = f.f_code.co_filename
linecache.checkcache(filename)
line = linecache.getline(filename, lineno, f.f_globals)
log(
INFO, 'EXCEPTION IN ({}, LINE {} "{}"): {}'.format(
filename, lineno, line.strip(), exc_obj))
log(action_logging_enum=WARNING, logging_text=str(e))
log(action_logging_enum=WARNING, logging_text=str(e.__traceback__))
return 0
log(action_logging_enum=INFO,
logging_text="[ADAPTIVE BOOSTING]: Result for URL [{u}] = {l}".format(
u=str(url), l=result))
return result
def predict_url(url):
support_vector_machine = load_model()
x_pred = pd.DataFrame(extract_features_from_URL(url, "PREDICT", True))
x_pred = transform_data(x_pred)
y_pred = support_vector_machine.predict(x_pred)
result = "NO RESULT"
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
log(action_logging_enum=INFO,
logging_text="[SUPPORT VECTOR MACHINE]: Result for URL [{u}] = {l}".format(u=url, l=result))
return result
def predict_url(url):
logistic_regression = load_model()
x_pred = pd.DataFrame(extract_features_from_URL(url, "PREDICT", True))
x_pred = transform_data(x_pred)
y_pred = logistic_regression.predict(x_pred)
result = "NO RESULT"
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
log(action_logging_enum=INFO,
logging_text="[LOGISTIC REGRESSION]: Result for URL [{u}] = {l}".format(u=url, l=result))
return result
def predict_url(url):
knn = load_model()
x_pred = pd.DataFrame(extract_features_from_URL(url, "PREDICT", True))
x_pred = transform_data(x_pred)
y_pred = knn.predict(x_pred)
result = "NO RESULT"
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
log(action_logging_enum=INFO,
logging_text="[K-NEAREST NEIGHBOR]: Result for URL [{u}] = {l}".format(
u=url, l=result))
def predict_url(url):
decision_tree = load_model()
x_pred = pd.DataFrame(extract_features_from_URL(url, "PREDICT", True))
x_pred = transform_data(x_pred)
y_pred = decision_tree.predict(x_pred)
result = "NO RESULT"
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
log(action_logging_enum=INFO,
logging_text="[DECISION TREE]: Result for URL [{u}] = {l}".format(
u=url, l=result))
return result
def predict_url(url):
try:
features = mod_feature_extraction.extract_features_from_URL(
url, "PREDICT", True)
x_pred = pd.DataFrame(features)
for index, col in enumerate(x_pred.columns):
if x_pred[col].dtype == np.bool:
name = x_pred.iloc[:, index].name
x_pred[name] = x_pred[name].astype(int)
x_pred = x_pred.drop(["Label", "ID", "URL", "Final URL"], axis=1)
y_pred = extreme_gradient_pre_loaded.predict(x_pred)
result = "NO RESULT"
int_result = 0
if str(y_pred[0]) == "0":
result = "Benign"
if str(y_pred[0]) == "1":
result = "Phish"
int_result = 1
except Exception as e:
exc_type, exc_obj, tb = sys.exc_info()
f = tb.tb_frame
lineno = tb.tb_lineno
filename = f.f_code.co_filename
linecache.checkcache(filename)
line = linecache.getline(filename, lineno, f.f_globals)
log(
ERROR, 'EXCEPTION IN ({}, LINE {} "{}"): {}'.format(
filename, lineno, line.strip(), exc_obj))
log(action_logging_enum=WARNING, logging_text=str(e))
log(action_logging_enum=WARNING, logging_text=str(e.__traceback__))
return 0
log(action_logging_enum=INFO,
logging_text="[EXTREME GRADIENT BOOSTING]: Result for URL [{u}] = {l}".
format(u=str(url), l=result))
return int_result
def predict_url(url, proba=False):
try:
if isinstance(url, str):
features = mod_feature_extraction.extract_features_from_URL(
url, "PREDICT", True)
x_pred = pd.DataFrame(features)
else:
x_pred = url
x_pred = x_pred[[
'Entropy', 'Ratio Netloc/URL', 'Length URL', 'Ratio Digit/Letter',
'Ratio Path/URL', 'Has HTTPS', 'Length Netloc', 'KL Divergence',
'Ratio Vowel/Consonant', 'Number Symbols', 'Number Dots',
'Number Tokens Netloc', 'Number Digits Path', 'Ratio Cap/NonCap',
'Number Dash', 'Number Dash Netloc', 'Has Token Netloc',
'Number Slash Path', 'Ratio Query/URL', 'Number Digits Netloc',
'Number Redirects', 'Number PhishyTokens Path',
'Has Digits Netloc', 'Number Query Parameters',
'Number Dots Netloc', 'Has Query', 'Number Equals',
'Number Semicolon', 'Number Ampersand', 'Cert Created Shortly',
'Number Stars'
]]
if proba:
y_pred = random_forest_pre_loaded.predict_proba(x_pred)
else:
y_pred = random_forest_pre_loaded.predict(x_pred)
return y_pred
except Exception as e:
exc_type, exc_obj, tb = sys.exc_info()
f = tb.tb_frame
lineno = tb.tb_lineno
filename = f.f_code.co_filename
linecache.checkcache(filename)
line = linecache.getline(filename, lineno, f.f_globals)
print('EXCEPTION IN ({}, LINE {} "{}"): {}'.format(
filename, lineno, line.strip(), exc_obj))
log(action_logging_enum=WARNING, logging_text=str(e))
log(action_logging_enum=WARNING, logging_text=str(e.__traceback__))
return None
