v1.0

Author: Coldwave96

check.py

@@ -1,6 +1,4 @@
 import os
-import re
-import numpy as np
 
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction.text import TfidfTransformer
@@ -57,23 +55,23 @@ def check_webshell(dir):
         for filename in filelist:
             fulpath=os.path.join(path, filename)
             all += 1
-            if filename.endswith('.php'):
+            if filename.endswith('.php') or filename.endswith('.txt'):
                 all_php += 1
                 t = load_str(fulpath)
                 t_list=[]
                 t_list.append(t)
                 x = CV1.transform(t_list).toarray()
                 x = transformer.fit_transform(x).toarray()
                 y_pred = clf1.predict(x)
-            elif filename.endswith('.asp'):
+            elif filename.endswith('.asp') or filename.endswith('.txt'):
                 all_asp += 1
                 t = load_str(fulpath)
                 t_list=[]
                 t_list.append(t)
                 x = CV2.transform(t_list).toarray()
                 x = transformer.fit_transform(x).toarray()
                 y_pred = clf2.predict(x)
-            elif filename.endswith('.jsp'):
+            elif filename.endswith('.jsp') or filename.endswith('.txt'):
                 all_jsp += 1
                 t = load_str(fulpath)
                 t_list=[]

train_asp.py

@@ -1,6 +1,4 @@
-import re
 import os
-import numpy as np
 
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.model_selection import train_test_split
@@ -32,7 +30,7 @@ def load_files(dir):
     g = os.walk(dir)
     for path, d, filelist in g:
         for filename in filelist:
-            if filename.endswith('.asp') or filename.endswith('.txt'):
+            if filename.endswith('.asp'):
                 fulpath = os.path.join(path, filename)
                 print "Load %s" % fulpath
                 t = load_str(fulpath)

train_jsp.py

@@ -1,6 +1,4 @@
-import re
 import os
-import numpy as np
 
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.model_selection import train_test_split
@@ -32,7 +30,7 @@ def load_files(dir):
     g = os.walk(dir)
     for path, d, filelist in g:
         for filename in filelist:
-            if filename.endswith('.jsp') or filename.endswith('txt'):
+            if filename.endswith('.jsp'):
                 fulpath = os.path.join(path, filename)
                 print "Load %s" % fulpath
                 t = load_str(fulpath)

train_php.py

@@ -1,6 +1,4 @@
-import re
 import os
-import numpy as np
 
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.model_selection import train_test_split
@@ -32,7 +30,7 @@ def load_files(dir):
     g = os.walk(dir)
     for path, d, filelist in g:
         for filename in filelist:
-            if filename.endswith('.php') or filename.endswith('.txt'):
+            if filename.endswith('.php'):
                 fulpath = os.path.join(path, filename)
                 print "Load %s" % fulpath
                 t = load_str(fulpath)