From e7f7ecd2b7ad4092722e6753e2533e81788d492c Mon Sep 17 00:00:00 2001
From: root <root@srv-share.kmpr.local>
Date: Mon, 24 Oct 2022 13:01:54 +0200
Subject: [PATCH] script now searches subdirectories too #1

---
 DuplicateRemover.py | 41 +++++++++++++++++++++--------------------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/DuplicateRemover.py b/DuplicateRemover.py
index 0048079..0c98140 100644
--- a/DuplicateRemover.py
+++ b/DuplicateRemover.py
@@ -4,10 +4,10 @@ import os
 import numpy as np
 import csv
 
-def writeCSV(dirname, i1, i2):
+def writeCSV(i1, i2):
     with open("duplicates.csv", "a") as file:
         writer = csv.writer(file, delimiter=',')
-        writer.writerow([dirname+i1, dirname+i2])
+        writer.writerow([i1, i2])
 
 class DuplicateRemover:
     extensions = ['png', 'jpg', 'jpeg', 'gif', 'webp']
@@ -20,26 +20,27 @@ class DuplicateRemover:
         Find and Delete Duplicates
         """
         
-        fnames = os.listdir(self.dirname)
+        #fnames = os.listdir(self.dirname)
         hashes = {}
         duplicates = []
         if verbose:
             print("Finding Duplicates Now!\n")
-        for image in fnames:
-            if list(image.lower().split('.'))[-1] in self.extensions:
-                try:
-                    with Image.open(os.path.join(self.dirname,image)) as img:
-                        temp_hash = imagehash.average_hash(img, self.hash_size)
-                        if temp_hash in hashes:
-                            if verbose:
-                                print("Duplicate {} \nfound for Image {}!\n".format(image,hashes[temp_hash]))
-                            if exportCSV:
-                                writeCSV(self.dirname, image, hashes[temp_hash])
-                            duplicates.append(image)
-                        else:
-                            hashes[temp_hash] = image
-                except Exception as error:
-                    print("Error: The following error occured:\n",image,"\n",error,"\n")
+        for path, subdirs, fnames in os.walk(self.dirname):
+            for image in fnames:
+                if list(image.lower().split('.'))[-1] in self.extensions:
+                    try:
+                        with Image.open(os.path.join(path,image)) as img:
+                            temp_hash = imagehash.average_hash(img, self.hash_size)
+                            if temp_hash in hashes:
+                                if verbose:
+                                    print("Duplicate {} \nfound for Image {}!\n".format(os.path.join(path,image),os.path.join(path,hashes[temp_hash])))
+                                if exportCSV:
+                                    writeCSV(os.path.join(path,image), os.path.join(path,hashes[temp_hash]))
+                                duplicates.append(os.path.join(path,image))
+                            else:
+                                hashes[temp_hash] = os.path.join(path,image)
+                    except Exception as error:
+                        print("Error: The following error occured:\n",os.path.join(path,image),"\n",error,"\n")
                    
         if len(duplicates) != 0:
             if verbose:
@@ -49,9 +50,9 @@ class DuplicateRemover:
             space_saved = 0
             if(a.strip().lower() == "y"):
                 for duplicate in duplicates:
-                    space_saved += os.path.getsize(os.path.join(self.dirname,duplicate))
+                    space_saved += os.path.getsize(duplicate)
                     
-                    os.remove(os.path.join(self.dirname,duplicate))
+                    os.remove(duplicate)
                     if verbose:
                         print("{} Deleted Succesfully!".format(duplicate))