MediaWiki Delete Duplicate Files Script

Delete_Duplicate_Files.py

#!/usr/bin/python3

import requests
import json
import mwclient

################### CONFIGURE ME ###################
site = mwclient.Site('YOUR_WEBSITE.com', path='/wiki/')
site.login(username='USERNAME_HERE', password='PASSWORD_HERE')
URL = "https://YOUR_WEBSITE.com/wiki/api.php"
####################################################

S = requests.Session()
PARAMS = {
    "action": "query",
    "list": "querypage",
    "qppage": "ListDuplicatedFiles",
    "qplimit": "100", #500 max
    "format": "json"
}

R = S.get(url=URL, params=PARAMS)
pages_with_duplicates_json = R.json()
title_list = ""

for result in pages_with_duplicates_json['query']['querypage']['results']:
    title = result['title']

    ### Remove the following two lines to proceed without asking
    print(f"Replace {title}? [Y/n]")
    if (input("") == ''):
        title_list += result['title'] + "|"

title_list = title_list[:-1]

if (title_list == ""):
    print("No pages with duplicates found.")
    quit()

print("\n" + title_list + "\n")

PARAMS = {
    "action": "query",
    "titles": title_list,
    "prop": "duplicatefiles",
    "format": "json"
}

R = S.get(url=URL, params=PARAMS)
data = R.json()

# Uncomment to see pages that will be replaced beforehand
#print(data)
#input("Press Enter to continue...")

# Loop through the JSON data and process duplicate files
for page_id, page_data in data['query']['pages'].items():
    original_file = page_data['title']
    try:
        duplicate_files = page_data['duplicatefiles']
    except:
        print("No more duplicate files found")
        quit()

    for duplicate_file in duplicate_files:
        duplicate_name = "File:" + duplicate_file['name']

        # Get information about the duplicate file
        duplicate_page = site.pages[duplicate_name]

        # Check if the duplicate file exists
        if duplicate_page.exists:
            # Delete the duplicate file
            duplicate_page.delete(reason='Duplicate file - redirecting to original')

            # Edit the deleted file's page content to redirect to the original file
            redirect_text = f"#REDIRECT [[{original_file}]]"
            duplicate_page.save(redirect_text, summary='Redirecting duplicate file to original')

            print(f"Redirected {duplicate_name} to {original_file} and deleted the duplicate.")
        else:
            print(f"{duplicate_name} doesn't exist.")

This script locates duplicate files (File:), deletes them, then sets the deleted page to redirect to the original file.
By default, it will ask you for each file, but you can remove lines 30 and 31 to have it delete all of them.