Update featureExtractor.py

featureExtractor.py

@@ -3,18 +3,19 @@ from urllib.parse import urlparse
 import httpx
 import pickle as pk
 import pandas as pd
+import extractorFunctions as ef
 
 #Function to extract features
 def featureExtraction(url):
 
   features = []
   #Address bar based features (12)
-  features.append(getLength(url))
-  features.append(getDepth(url))
-  features.append(tinyURL(url))
-  features.append(prefixSuffix(url))
-  features.append(no_of_dots(url))
-  features.append(sensitive_word(url))
+  features.append(ef.getLength(url))
+  features.append(ef.getDepth(url))
+  features.append(ef.tinyURL(url))
+  features.append(ef.prefixSuffix(url))
+  features.append(ef.no_of_dots(url))
+  features.append(ef.sensitive_word(url))
 
 
   domain_name = ''
@@ -25,8 +26,8 @@ def featureExtraction(url):
   except:
     dns = 1
 
-  features.append(1 if dns == 1 else domainAge(domain_name))
-  features.append(1 if dns == 1 else domainEnd(domain_name))
+  features.append(1 if dns == 1 else ef.domainAge(domain_name))
+  features.append(1 if dns == 1 else ef.domainEnd(domain_name))
 
   # HTML & Javascript based features (4)
   dom = []
@@ -35,11 +36,11 @@ def featureExtraction(url):
   except:
     response = ""
 
-  dom.append(iframe(response))
-  dom.append(mouseOver(response))
-  dom.append(forwarding(response))
+  dom.append(ef.iframe(response))
+  dom.append(ef.mouseOver(response))
+  dom.append(ef.forwarding(response))
 
-  features.append(has_unicode(url)+haveAtSign(url)+havingIP(url))
+  features.append(ef.has_unicode(url)+ef.haveAtSign(url)+ef.havingIP(url))
 
   with open('pca_model.pkl', 'rb') as file:
     pca = pk.load(file)