vhsu · August 13, 2024 13:15
diff --git a/imgremovedups.py b/imgremovedups.py
 """
 Script to Remove Duplicate Images from a Folder

 This script identifies and removes duplicate images within a specified folder.
 It uses perceptual hashing to generate a unique fingerprint for each image, 
 allowing it to detect duplicates even if the files have different names or formats.

 What the Code Does:
 -------------------
 1. Scans the specified folder for image files (supports common formats such as 
   .jpg, .jpeg, .png, .bmp, .gif, .tiff, .webp).
 2. Computes a perceptual hash for each image to identify duplicates.
 3. If two images share the same hash, one of the duplicates is removed.
 4. Prints the names of the duplicate files that were found and removed.

 How to Use:
 -----------
 1. Save this script as a Python file, e.g., `remove_duplicates.py`.
 2. Run the script using Python.
 3. You will be prompted to enter the path of the folder containing the images 
   you want to check for duplicates.
 4. The script will process the images in the folder, removing any duplicates 
   it finds and printing the results to the console.

 Example:
 --------
 $ python remove_duplicates.py
 Enter the path to the folder: /path/to/your/image/folder

 Dependencies:
 -------------
 - Python 3.x
 - PIL (Pillow)
 - imagehash

 Make sure to install the required packages using pip if they are not already installed:
 $ pip install pillow imagehash
 """

 import os
 from PIL import Image
 import imagehash

 def image_hash(filepath):
    """Returns the perceptual hash of the image file.

    Args:
        filepath (str): The path to the image file.

    Returns:
        str: The perceptual hash of the image.
    """
    with Image.open(filepath) as img:
        return str(imagehash.phash(img))

 def main(folder_path):
    """Removes duplicate images in the specified folder.

    This function computes the perceptual hash of each image in the given folder
    and deletes any images that have the same hash (i.e., duplicate images).

    Args:
        folder_path (str): The path to the folder containing images.
    """
    if not os.path.exists(folder_path):
        print("Folder not found!")
        return

    duplicates = []
    hash_keys = dict()

    # Define a set of common image file extensions
    image_extensions = {'.jpg', '.jpeg', '.png', '.bmp', '.gif', '.tiff', '.webp'}

    # Iterate through each image in the folder
    for filename in os.listdir(folder_path):
        file_path = os.path.join(folder_path, filename)
        
        # Check if the file is an image by its extension
        if os.path.isfile(file_path) and os.path.splitext(filename)[1].lower() in image_extensions:
            try:
                img_hash = image_hash(file_path)
                if img_hash in hash_keys:
                    print(f"Duplicate found: {filename}")
                    duplicates.append(file_path)
                else:
                    hash_keys[img_hash] = filename
            except IOError:
                # Handle the exception if the file is not a valid image
                print(f"Cannot open {filename} as an image.")
    
    # Remove duplicates
    for duplicate_file in duplicates:
        os.remove(duplicate_file)
        print(f"Removed: {duplicate_file}")

    print("Duplicate removal complete.")

 if __name__ == '__main__':
    folder_path = input("Enter the path to the folder: ")  # Prompt the user for the folder path
    main(folder_path)
	"""
	Script to Remove Duplicate Images from a Folder

	This script identifies and removes duplicate images within a specified folder.
	It uses perceptual hashing to generate a unique fingerprint for each image,
	allowing it to detect duplicates even if the files have different names or formats.

	What the Code Does:
	-------------------
	1. Scans the specified folder for image files (supports common formats such as
	.jpg, .jpeg, .png, .bmp, .gif, .tiff, .webp).
	2. Computes a perceptual hash for each image to identify duplicates.
	3. If two images share the same hash, one of the duplicates is removed.
	4. Prints the names of the duplicate files that were found and removed.

	How to Use:
	-----------
	1. Save this script as a Python file, e.g., `remove_duplicates.py`.
	2. Run the script using Python.
	3. You will be prompted to enter the path of the folder containing the images
	you want to check for duplicates.
	4. The script will process the images in the folder, removing any duplicates
	it finds and printing the results to the console.

	Example:
	--------
	$ python remove_duplicates.py
	Enter the path to the folder: /path/to/your/image/folder

	Dependencies:
	-------------
	- Python 3.x
	- PIL (Pillow)
	- imagehash

	Make sure to install the required packages using pip if they are not already installed:
	$ pip install pillow imagehash
	"""

	import os
	from PIL import Image
	import imagehash

	def image_hash(filepath):
	"""Returns the perceptual hash of the image file.

	Args:
	filepath (str): The path to the image file.

	Returns:
	str: The perceptual hash of the image.
	"""
	with Image.open(filepath) as img:
	return str(imagehash.phash(img))

	def main(folder_path):
	"""Removes duplicate images in the specified folder.

	This function computes the perceptual hash of each image in the given folder
	and deletes any images that have the same hash (i.e., duplicate images).

	Args:
	folder_path (str): The path to the folder containing images.
	"""
	if not os.path.exists(folder_path):
	print("Folder not found!")
	return

	duplicates = []
	hash_keys = dict()

	# Define a set of common image file extensions
	image_extensions = {'.jpg', '.jpeg', '.png', '.bmp', '.gif', '.tiff', '.webp'}

	# Iterate through each image in the folder
	for filename in os.listdir(folder_path):
	file_path = os.path.join(folder_path, filename)

	# Check if the file is an image by its extension
	if os.path.isfile(file_path) and os.path.splitext(filename)[1].lower() in image_extensions:
	try:
	img_hash = image_hash(file_path)
	if img_hash in hash_keys:
	print(f"Duplicate found: {filename}")
	duplicates.append(file_path)
	else:
	hash_keys[img_hash] = filename
	except IOError:
	# Handle the exception if the file is not a valid image
	print(f"Cannot open {filename} as an image.")

	# Remove duplicates
	for duplicate_file in duplicates:
	os.remove(duplicate_file)
	print(f"Removed: {duplicate_file}")

	print("Duplicate removal complete.")

	if __name__ == '__main__':
	folder_path = input("Enter the path to the folder: ") # Prompt the user for the folder path
	main(folder_path)