Update file

URLFeatureExtraction.py

@@ -178,7 +178,7 @@ def forwarding(response):
     else:
       return 1
 
-state = 0
+flag = False
 def featureExtraction(url):
 
   new_url = url
@@ -199,7 +199,7 @@ def featureExtraction(url):
         response = ""
     
   url = new_url
-  print("URL", url)
+  print("URL:\t", url)
 
   features = []
   features.append(havingIP(url))
@@ -212,15 +212,16 @@ def featureExtraction(url):
   features.append(prefixSuffix(url))
   
   try:
-    global state
+    global flag
 
     domain_name = whois.whois(urlparse(url).netloc)
 
     if domain_name.get('domain_name'):
-      state = 0
+      pass
 
     else:
-      state = 1
+      flag = True
+
     dns = 0 if socket.gethostbyname(domain_name.domain_name[0]) else 1
   except:
     dns = 1
@@ -239,22 +240,4 @@ def featureExtraction(url):
 
 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.
+                      'Domain_Age', 'Domain_End', 'iFrame', 'Mouse_Over','Right_Click', 'Web_Forwards', 'Label']

app.py

@@ -17,10 +17,9 @@ def isPhishing(link):
 
     features = URLFeatureExtraction.featureExtraction(link)
     print(features)
-    
     prediction = model2.predict([features])
-    print(prediction)
-
+    print(prediction[0])
+    
     df = df._append({'URL': link, 'Phishy?': "UnSafe" if prediction[0] else "Safe"}, ignore_index=True)
     return prediction[0]
 
@@ -32,17 +31,25 @@ def check_URL(Email):
     extractor = URLExtract()
     urls = extractor.find_urls(Email)
     n_urls = len(urls)
+
+    if not urls: return -1
     if urls:
         bad_urls = sum([isPhishing(url) for url in urls])
     else:
         bad_urls = 0
-    print("Out of {} urls {} are phishing".format(n_urls, bad_urls))
+    print("Out of {} urls {} are legitimate.".format(n_urls, n_urls - bad_urls))
 
     return bad_urls
 
 def check_Mail(Email):
-    state = max(URLFeatureExtraction.state, 0)
-    return [isSpam(Email), check_URL(Email), state, df]
+    bad_urls = check_URL(Email)
+    if bad_urls==-1:
+        return [isSpam(Email), 0, 'Safe', df]
+    
+    if URLFeatureExtraction.flag or bad_urls:
+        return [isSpam(Email), bad_urls, 'Risky', df]
+    
+    return [isSpam(Email), bad_urls, 'Safe', df]
 
 iface = gr.Interface(
     fn=check_Mail,
@@ -54,6 +61,4 @@ iface = gr.Interface(
         gr.Dataframe(label="Insights", interactive=False)
     ]
 )
-
-# Launch the Gradio app
 iface.launch()