URLFeatureExtraction.py

import urllib
import ipaddress
import re
import socket
from bs4 import BeautifulSoup
import whois
import requests
import urllib.request
from urllib.parse import urlparse
from datetime import datetime

def havingIP(url):
  try:
    ipaddress.ip_address(url)
    ip = 1
  except:
    ip = 0
  return ip

def haveAtSign(url):
  if "@" in url:
    at = 1    
  else:
    at = 0    
  return at


def getLength(url):
  if len(url) < 54:
    return 1         
  else:
    return 0

def getDepth(url):
  s = urlparse(url).path.split('/')
  depth = 0
  for j in range(len(s)):
    if len(s[j]) != 0:
      depth +=1
  return depth

def redirection(url):
  pos = url.rfind('//')
  if pos > 6:
    if pos > 7:
      return 1
    else:
      return 0
  else:
    return 0
  
def httpDomain(url):
  domain = urlparse(url).netloc
  if 'https' in domain:
    return 1
  else:
    return 0
  
shortening_services = r"bit\.ly|goo\.gl|shorte\.st|go2l\.ink|x\.co|ow\.ly|t\.co|tinyurl|tr\.im|is\.gd|cli\.gs|" \
                      r"yfrog\.com|migre\.me|ff\.im|tiny\.cc|url4\.eu|twit\.ac|su\.pr|twurl\.nl|snipurl\.com|" \
                      r"short\.to|BudURL\.com|ping\.fm|post\.ly|Just\.as|bkite\.com|snipr\.com|fic\.kr|loopt\.us|" \
                      r"doiop\.com|short\.ie|kl\.am|wp\.me|rubyurl\.com|om\.ly|to\.ly|bit\.do|t\.co|lnkd\.in|db\.tt|" \
                      r"qr\.ae|adf\.ly|goo\.gl|bitly\.com|cur\.lv|tinyurl\.com|ow\.ly|bit\.ly|ity\.im|q\.gs|is\.gd|" \
                      r"po\.st|bc\.vc|twitthis\.com|u\.to|j\.mp|buzurl\.com|cutt\.us|u\.bb|yourls\.org|x\.co|" \
                      r"prettylinkpro\.com|scrnch\.me|filoops\.info|vzturl\.com|qr\.net|1url\.com|tweez\.me|v\.gd|" \
                      r"tr\.im|link\.zip\.net"

def tinyURL(url):
    match=re.search(shortening_services,url)
    if match:
        return 1
    else:
        return 0


def prefixSuffix(url):
    if '-' in urlparse(url).netloc:
        return 1        
    else:
        return 0        

def web_traffic(url):
  try:
    query = urllib.parse.quote(url)
    search_url = f"https://www.google.com/search?q=site:{query}"

    headers = {'User-Agent': 'Mozilla/5.0'}
    req = urllib.request.Request(search_url, headers=headers)
    response = urllib.request.urlopen(req).read()
    soup = BeautifulSoup(response, "lxml")
    
    results = soup.find_all('div', class_='BNeawe')
    
    for result in results:
        if 'did not match' in result.get_text():
            return 0
        
    return 1
  
  except Exception as e:
      print(f"Error: {e}")
      return 0

def domainAge(domain_name):
  creation_date = domain_name.creation_date
  expiration_date = domain_name.expiration_date
  if (isinstance(creation_date,str) or isinstance(expiration_date,str)):
    try:
      creation_date = datetime.strptime(creation_date,'%Y-%m-%d')
      expiration_date = datetime.strptime(expiration_date,"%Y-%m-%d")
    except:
      return 1
  if ((expiration_date is None) or (creation_date is None)):
      return 1
  elif ((type(expiration_date) is list) or (type(creation_date) is list)):
      return 1
  else:
    ageofdomain = abs((expiration_date - creation_date).days)
    if ((ageofdomain/30) < 6):
      age = 1
    else:
      age = 0
  return age

def domainEnd(domain_name):
  expiration_date = domain_name.expiration_date
  if isinstance(expiration_date,str):
    try:
      expiration_date = datetime.strptime(expiration_date,"%Y-%m-%d")
    except:
      return 1
  if (expiration_date is None):
      return 1
  elif (type(expiration_date) is list):
      return 1
  else:
    today = datetime.now()
    end = abs((expiration_date - today).days)
    if ((end/30) < 6):
      end = 0
    else:
      end = 1
  return end

def iframe(response):
  if response == "":
      return 1
  else:
      if re.findall(r"[<iframe>|<frameBorder>]", response.text):
          return 0
      else:
          return 1

def mouseOver(response): 
  if response == "" :
    return 1
  else:
    if re.findall("<script>.+onmouseover.+</script>", response.text):
      return 1
    else:
      return 0

def rightClick(response):
  if response == "":
    return 1
  else:
    if re.findall(r"event.button ?== ?2", response.text):
      return 0
    else:
      return 1
 
def forwarding(response):
  if response == "":
    return 1
  else:
    if len(response.history) <= 2:
      return 0
    else:
      return 1

state = 0
def featureExtraction(url):

  new_url = url
  try:
    response = requests.get(new_url)

  except:
    try:
      new_url = 'https://' + url
      response = requests.get(new_url)

    except:
      try:
        new_url = 'http://' + url
        response = requests.get(new_url)

      except:
        response = ""
    
  url = new_url
  print("URL", url)

  features = []
  features.append(havingIP(url))
  features.append(haveAtSign(url))
  features.append(getLength(url))
  features.append(getDepth(url))
  features.append(redirection(url))
  features.append(httpDomain(url))
  features.append(tinyURL(url))
  features.append(prefixSuffix(url))
  
  try:
    global state

    domain_name = whois.whois(urlparse(url).netloc)

    if domain_name.get('domain_name'):
      state = 0

    else:
      state = 1
    dns = 0 if socket.gethostbyname(domain_name.domain_name[0]) else 1
  except:
    dns = 1

  features.append(dns)
  features.append(web_traffic(url))
  features.append(1 if dns == 1 else domainAge(domain_name))
  features.append(1 if dns == 1 else domainEnd(domain_name))

  features.append(iframe(response))
  features.append(mouseOver(response))
  features.append(rightClick(response))
  features.append(forwarding(response))
  
  return features

feature_names = ['Domain', 'Have_IP', 'Have_At', 'URL_Length', 'URL_Depth','Redirection', 
                      'https_Domain', 'TinyURL', 'Prefix/Suffix', 'DNS_Record', 'Web_Traffic', 
                      'Domain_Age', 'Domain_End', 'iFrame', 'Mouse_Over','Right_Click', 'Web_Forwards', 'Label']

# I @ L D R D t P D T A E i M R F  L
#     . .         . . .         .

# 0,0,1,3,0,0,0,0,0,1,0,1,0,0,1,0  0
# 0,0,1,1,0,0,0,0,0,1,0,1,0,0,1,0  Y
# 0,0,0,1,0,0,0,0,1,0,1,1,0,0,1,0  -

#                         . .   
# 0,0,1,1,0,0,0,0,1,1,1,1,1,1,1,1  0
# 0,0,1,0,0,0,0,0,0,1,1,1,0,0,1,0
# 0,0,0,0,0,0,0,0,1,0,1,1,0,0,1,0  -

# 0,0,1,3,0,0,0,0,0,0,1,1,0,0,1,0  1
# 0,0,1,0,0,0,0,0,0,0,1,1,0,0,1,0
# 0,0,0,0,0,0,0,0,1,1,1,1,0,0,1,0  -

# Prints : site. history. array. pred.