43

APPENDICES

A. Project Gantt Chart

B. Relevant Source Code
C. User’s Guide
D. Evaluation Tool
E. Endorsement
F. IMRAD
G. IT Expert’s Resume
H. Curriculum Vitae
 44

Appendix A
Project Gantt Chart
 45

A. Project Gantt Chart

 46

Appendix B
Relevant Source Code
 47

B. Relevant Source Code

App.py
#importing required libraries

from flask import Flask, request, render_template

import numpy as np
import pandas as pd
from sklearn import metrics
import warnings
warnings.filterwarnings('ignore')
from feature import generate_data_set
# Gradient Boosting Classifier Model
from sklearn.ensemble import GradientBoostingClassifier

data = pd.read_csv("phishing.csv")
#droping index column
data = data.drop(['Index'],axis = 1)
# Splitting the dataset into dependant and independant fetature

X = data.drop(["class"],axis =1)
y = data["class"]

# instantiate the model

gbc = GradientBoostingClassifier(max_depth=4,learning_rate=0.7)

# fit the model

gbc.fit(X,y)

app = Flask(_name_)

@app.route("/")
def index():
return render_template("index.html", xx= -1)

@app.route("/predict", methods=["GET", "POST"])

def predict():
if request.method == "POST":

Features
import ipaddress
import re
import urllib.request
from bs4 import BeautifulSoup
import socket
 48

import requests
from googlesearch import search
import whois
from datetime import date, datetime
import time
from dateutil.parser import parse as date_parse

def diff_month(d1, d2):

return (d1.year - d2.year) * 12 + d1.month - d2.month

def generate_data_set(url):

data_set = []

if not re.match(r"^https?", url):

url = "http://" + url

try:
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
except:
response = ""
soup = -999

domain = re.findall(r"://([^/]+)/?", url)[0]

if re.match(r"^www.", domain):
domain = domain.replace("www.", "")
whois_response = whois.whois(domain)

rank_checker_response =
requests.post("https://www.checkpagerank.net/index.php", {
"name": domain
})

try:
global_rank = int(re.findall(
r"Global Rank: ([0-9]+)", rank_checker_response.text)[0])
except:
global_rank = -1

# 1.UsingIP
try:
ipaddress.ip_address(url)
data_set.append(-1)
except:
 49

data_set.append(1)

# 2.LongURL
if len(url) < 54:
data_set.append(1)
elif len(url) >= 54 and len(url) <= 75:
data_set.append(0)
else:
data_set.append(-1)

# 3.ShortURL
match =
re.search('bit\.ly|goo\.gl|shorte\.st|go2l\.ink|x\.co|ow\.ly|t\.co|tinyurl|tr\.im|is\.gd|cli\.
gs|'
'yfrog\.com|migre\.me|ff\.im|tiny\.cc|url4\.eu|twit\.ac|su\.pr|twurl\.nl|s
nipurl\.com|'
'short\.to|BudURL\.com|ping\.fm|post\.ly|Just\.as|bkite\.com|snipr\.c
om|fic\.kr|loopt\.us|'
'doiop\.com|short\.ie|kl\.am|wp\.me|rubyurl\.com|om\.ly|to\.ly|bit\.do|
t\.co|lnkd\.in|'
'db\.tt|qr\.ae|adf\.ly|goo\.gl|bitly\.com|cur\.lv|tinyurl\.com|ow\.ly|bit\.ly|
ity\.im|'
'q\.gs|is\.gd|po\.st|bc\.vc|twitthis\.com|u\.to|j\.mp|buzurl\.com|cutt\.u
s|u\.bb|yourls\.org|'
'x\.co|prettylinkpro\.com|scrnch\.me|filoops\.info|vzturl\.com|qr\.net|
1url\.com|tweez\.me|v\.gd|tr\.im|link\.zip\.net', url)
if match:
data_set.append(-1)
else:
data_set.append(1)

Gradientboostclassifier
#importing required libraries

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import metrics
import warnings
warnings.filterwarnings('ignore')

#Loading Data
 50

data = pd.read_csv("phishing.csv")
data.head()

#Listing the features of the dataset

data.columns

#Information about the dataset

data.info()

#nunique values in columns

data.nunique()

#droping index column

data = data.drop(['Index'],axis = 1)

#description of dataset

data.describe().T

#Splitting the dataset into dependant and independant features

X = data.drop(["class"],axis =1)
y = data["class"]

#Splitting the dataset into train and test sets: 80-20 split

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 = 42)
X_train.shape, y_train.shape, X_test.shape, y_test.shape

#Model Building & Training

#Creating holders to store the model performance results

ML_Model = []
accuracy = []
f1_score = []
recall = []
precision = []

#function to call for storing the results

 51

def storeResults(model, a,b,c,d):

ML_Model.append(model)
accuracy.append(round(a, 3))
f1_score.append(round(b, 3))
recall.append(round(c, 3))
precision.append(round(d, 3))

#Gradient Boosting Classifier Model

from sklearn.ensemble import GradientBoostingClassifier

# instantiate the model

gbc = GradientBoostingClassifier(max_depth=4,learning_rate=0.7)

# fit the model

gbc.fit(X_train,y_train)

#predicting the target value from the model for the samples

y_train_gbc = gbc.predict(X_train)
y_test_gbc = gbc.predict(X_test)

HTML
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta name="description" content="This website is developed to identify the
safety of a url.">
<meta name="keywords" content="phishing url,phishing,cyber
security,machine learning,classifier,python">
<meta name="author" content="VJCET">

<!-- BootStrap -->

<link rel="stylesheet"
href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css"
integrity="sha384-
1BmE4kWBq78iYhFldvKuhfTAU6auU8tT94WrHftjDbrCEXSU1oBoqyl2QvZ6jIW3
" crossorigin="anonymous">
 52

<link href="static/styles.css" rel="stylesheet">

<title>Phishing Website Detection</title>
<script src="https://code.jquery.com/jquery-latest.min.js"></script>
</head>

<body>

<div class="main-body">
<div class="form" id="form1">

<br><br><br>
<form action="/predict" method ="post">
<input type="text" class="form__input" name ='url' id="url" placeholder="
Type a URL" required="" />
<button class="button" id="bxt" role="button" >Click here to
check</button>
</form>

<br>
<br>
</div>
<div class="hi" id="form2" >

<br>
<h6 class = "right "><a href= {{ url }} target="_blank">{{ url }}</a></h6>

<br>
<h3 id="prediction"></h3>
<button class="button2" id="button2"
role="button" onclick="window.location.replace('http://127.0.0.1:5000')"
target="_blank" > Continue ?</button>
<button class="button1" id="button1"
role="button" onclick="window.location.replace('http://127.0.0.1:5000')"
target="_blank">Continue?</button>
</div>
</div>

<!-- JavaScript -->

<script src="https://code.jquery.com/jquery-3.6.0.slim.min.js"
integrity="sha256-u7e5khyithlIdTpu22PHhENmPcRdFiHRjhAuHcs05RI="
crossorigin="anonymous"></script>
<script
src="https://cdn.jsdelivr.net/npm/[email protected]/dist/umd/popper.min.js"
integrity="sha384-
Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo"
crossorigin="anonymous"></script>
 53

<script
src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.min.js"
integrity="sha384-
QJHtvGhmr9XOIpI6YVutG+2QOK9T+ZnN4kzFN1RtK3zEFEIsxhlmWl5/YESvpZ
13"
crossorigin="anonymous"></script>

<script>

$('#form2').hide();
let x = '{{xx}}';
let num = x*100;
if (0<=x && x<0.50){
num = 100-num;
}
let txtx = num.toString();
if(x<=1 && x>=0.50){
var label = "Website is "+txtx +"% safe to use...";
document.getElementById("prediction").innerHTML = label;
document.getElementById("button1").style.display="block";
$('#form1').hide();
setTimeout(function()
{
$('#form2').show();
},1000);

}
else if (0<=x && x<0.50){
var label = "Website is "+txtx +"% unsafe to use..."
document.getElementById("prediction").innerHTML = label ;
document.getElementById("button2").style.display="block";
$('#form1').hide();
setTimeout(function()
{
$('#form2').show();
},1000);

}
</script>

</body>

</html>
 54

Appendix C
User’s Guide
 55

C. User's Guide

The product is a web-based system that detect a phishing website by

providing a URL. This aim to lessen the people who get deceive by
phishers or people who make phishing website. The system is just giving
a percentage whether the URL is safe or not but the decision will always
on the users.

User Interface Overview

There are three (3) main features;

 Input field – where the user input the URL.
 Check button – clicking it will start to assess the URL.
 Features table – the user can see where the URL matches
features (factors of a phishing website) and the percentage of the
website (URL) to be classified as a phishing website.

Using System’s Features

1. Paste the URL to “Input field” area.

 56

2. Click the “Check button”

 57

3. After assessing the URL, the system will show “This Website is
Safe to use” or “This Website is not safe to use”. Check the
“Features table” to see where the URL matches to features and its
percentage to be classified as phishing site.

4. Check the button “Check button” again to assess new URL.

 58

Appendix D
Evaluation Tool
 59

D. Evaluation Tool
60
61
62
63
64
65
66