def getResult(url):
#Importing dataset
# data = np.loadtxt("dataset.csv", delimiter = ",")
#Seperating features and labels
# X = data[: , :-1]
# y = data[: , -1]
#Seperating training features, testing features, training labels & testing labels
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
# clf = rfc()
clf = pickle.load(open("model/Nearest Neighbors.sav", 'rb'))
#clf.fit(X_train, y_train)
#score = clf.score(X_test, y_test)
#print(score*100)
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
try:
prediction = clf.predict(X_new)
if prediction == -1:
return "Phishing Url"
else:
return "Legitimate Url"
except:
return "Phishing Url"
def getResult(url):
#Importing dataset
filen = 'dataset.csv'
r = open(filen,'rt')
data = np.loadtxt(r, delimiter = ",") # loading the dataset
#lets seperating features and labels
X = data[: , :-1]
y = data[: , -1]
#Seperating training features, testing features, training labels & testing labels
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
clf = rfc()
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print(score*100) # accuracy score
X_new = []
X_input = url # checking for catogery
X_new=feature_extraction.generate_data_set(X_input) # extracting features of given url
X_new = np.array(X_new).reshape(1,-1) # converting
try:
prediction = clf.predict(X_new)
if prediction == -1:
return "Omg!!!.. its Phishing Url"
else:
return "hureeh!!....its a Genuine Url"
except:
return "Omg!!... its a Phishing Url"
def getResult(url):
dataset=pd.read_csv(r"phishing_dataset.csv")
dataset.drop(['index'],axis=1,inplace=True)
x=dataset.iloc[: ,0:30].values
y=dataset.iloc[: ,30:31].values
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
from sklearn.tree import DecisionTreeClassifier
classifier=DecisionTreeClassifier(random_state=0)
classifier.fit(x_train,y_train)
decisiontree=classifier.predict(x_test)
#from sklearn.metrics import confusion_matrix
#cm=confusion_matrix(y_test,decisiontree)
#import sklearn.metrics as metrics
#fpr,tpr,threshold=metrics.roc_curve(y_test,decisiontree)
#roc_auc=metrics.auc(fpr,tpr)
accuracy=accuracy_score(decisiontree,y_test)
print(accuracy*100)
x_new = []
x_input = url
x_new=feature_extraction.generate_data_set(x_input)
x_new = np.array(x_new).reshape(1,-1)
try:
prediction = classifier.predict(x_new)
if prediction == -1:
return "Phishing URL"
else:
return "Legitimate URL"
except:
return "Phishing URL"
def getResult(url):
#Importing dataset
"""data = np.loadtxt(r"dataset/dataset.csv", delimiter = ",")
#Seperating features and labels
X = data[: , :-1]
y = data[: , -1]
#Seperating training features, testing features, training labels & testing labels
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
clf = rfc()
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
#print(score*100)
pickle.dump(clf,open('model_random_forest.pkl','wb'))"""
model = pickle.load(open(r'trained-model/model_random_forest.pkl', 'rb'))
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
try:
prediction = model.predict(X_new)
if prediction == -1:
return "Phishing Website"
else:
return "Legitimate Website"
except:
return "Phishing Website"
def predict(url):
'''
#Importing dataset
data = np.loadtxt("dataset.csv", delimiter = ",")
#Seperating features and labels
X = data[: , :-1]
y = data[: , -1]
#Seperating training features, testing features, training labels & testing labels
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
clf = rfc()
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print(score*100)
with open('rfc.pkl', 'wb') as model_file:
pickle.dump(clf, model_file)
'''
with open('rfc.pkl', 'rb') as model_file:
model = pickle.load(model_file)
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
try:
prediction = model.predict(X_new)
if prediction == -1:
return 1
else:
return 0
except:
return 1
def getResult(url):
#Importing dataset
data = pd.read_csv('Dataset/dataset.csv', delimiter=",")
#Seperating features and labels
X = np.array(data.iloc[:, :-1])
y = np.array(data.iloc[:, -1])
print(type(X))
#Seperating training features, testing features, training labels & testing labels
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# classifier = RandomForestClassifier()
classifier = LogisticRegression()
classifier.fit(X_train, y_train)
score = classifier.score(X_test, y_test)
score = score * 100
print(score)
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
analysis_result = ""
try:
prediction = classifier.predict(X_new)
if prediction == -1:
analysis_result = "Phishing URL"
elif prediction == 0:
analysis_result = "Suspecious"
else:
analysis_result = "Legitimate URL"
except:
analysis_result = "Suspecious URL"
result_of_analysis = """<section class="iq-about overview-block-pt iq-hide">
<div class="container">
<div class="row align-items-end">
<div class="col-lg-8 col-md-12">
<div class="about-content">
<h1 class="text-about iq-tw-6">Result of Your URL : <span class="iq-font-green iq-fw-8">""" + url + """</span></h1>
<ul class="listing-mark iq-mtb-20 iq-tw-6 iq-font-black">
<li class="good">""" + analysis_result + """</li>
</ul>
<h5 class="iq-mt-20 iq-mb-20" style="color: #65d972;font-size: 16px;">Accuracy : """ + str(
score) + """</h5>
</div>
</div>
</div>
</div>
</section>
"""
return result_of_analysis
def getResult(url):
#model=pickle.load(open(r'trained-model/model_random_forest.pkl','rb'))
model = pickle.load(
open(r'trained-model/model_logistic_regression.pkl', 'rb'))
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
try:
prediction = model.predict(X_new)
if prediction == -1:
return "Phishing Website"
else:
return "Legitimate Website"
except:
return "Phishing Website"
def predict():
if request.method == 'POST':
url = request.form['url']
print(url)
X_new = []
X_input = url
X_new=feature_extraction.generate_data_set(X_input)
print(X_new)
X_new = np.array(X_new).reshape(1,-1)
print(X_new)
prediction = model.predict(X_new)
print(prediction)
output = prediction[0]
print(output)
if output == 1:
return render_template('index.html',prediction_text = "Good Url")
else:
return render_template('index.html',prediction_text = "Malicious Url")
def getResult(url):
#Importing dataset
data = np.loadtxt("dataset.csv", delimiter=",")
#Seperating features and labels
X = data[:, :-1]
y = data[:, -1]
#Seperating training features, testing features, training labels & testing labels
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
clf = rfc()
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print(score * 100)
#joblib.dump(clf, "randomForest.pkl")
#pickled_model = joblib.load("randomForest.pkl")
X_new = []
X_input = url
X_new = feature_extraction.generate_data_set(X_input)
X_new = np.array(X_new).reshape(1, -1)
try:
prediction = clf.predict(X_new)
if prediction == -1:
print('Phishing URL')
return "Phishing Url"
else:
print('Legitimate URL')
return "Legitimate Url"
except:
return "Phishing Url"
f = open('data.json', 'r+')
#try:
data = json.load(f)
#except:
# data = {}
#input url
url = input("Enter url:")
if url in data:
print(data[url])
exit()
#checking and predicting
else:
checkprediction = feature_extraction.generate_data_set(url)
f1.write(','.join(map(str, checkprediction)))
checkprediction = np.array(checkprediction).reshape(1, -1)
try:
prediction = classifier.predict(checkprediction)
print(prediction)
if prediction == -1:
data[url] = "Phishing Url"
else:
data[url] = "Legitimate Url"
except:
data[url] = "Phishing Url"
f.seek(0)
f.write(json.dumps(data))