User:DreamRimmer/commonsfileusage.py

"""
Copyright (c) 2025 DreamRimmer

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
"""

import requests, time, json

headers = {"User-Agent": "User:DreamRimmer (email:dreamrimmer.wikimedian@gmail.com) :en:WP:AIIMAGE"}
session = requests.Session()
session.headers.update(headers)

#retrieve files from category
def get_files(cat_name, cont_token=None):
    url = "https://commons.wikimedia.org/w/api.php"
    params = {
        "action": "query",
        "list": "categorymembers",
        "cmtitle": cat_name,
        "cmtype": "file|subcat",
        "cmlimit": "max",
        "format": "json",
        "maxlag": 5 # respect api
    }
    if cont_token:
        params["cmcontinue"] = cont_token
    response = session.get(url, params=params)
    try:
        return response.json()
    except json.JSONDecodeError:
        return None

# usage data for the files
def get_usage(file_names):
    url = "https://commons.wikimedia.org/w/api.php"
    params = {
        "action": "query",
        "format": "json",
        "prop": "globalusage",
        "titles": "|".join(file_names),
        "formatversion": "2",
        "guprop": "url|namespace",
        "gunamespace": "0",
        "gusite": "enwiki",
        "maxlag": 5
    }
    response = session.get(url, params=params)
    try:
        return response.json()
    except json.JSONDecodeError:
        return None

def process_cat(cat_name, processed_files=None, output_file=None):
    if processed_files is None:
        processed_files = set()
    cont_token = None
    while True:
        data = get_files(cat_name, cont_token)
        if data is None:
            break
        members = data.get("query", {}).get("categorymembers", [])
        files = [member["title"] for member in members if member["ns"] == 6 and member["title"] not in processed_files]
        subcats = [member["title"] for member in members if member["ns"] == 14]
        for i in range(0, len(files), 50): # process files in batches of 50
            batch = files[i:i+50]
            usage_data = get_usage(batch)
            if usage_data is None:
                continue
            pages = usage_data.get('query', {}).get('pages', [])
            for page in pages:
                if 'globalusage' in page:
                    for usage in page['globalusage']:
                        result = f"* [[:{page['title']}]] - [[{usage['title'].replace('_', ' ')}]]"
                        print(result)
                        if output_file:
                            output_file.write(result + "\n")

            processed_files.update(batch)
            time.sleep(5) # respect api

        for subcat in subcats:
            process_cat(subcat, processed_files, output_file)
        if "continue" in data:
            cont_token = data["continue"]["cmcontinue"]
        else:
            break

cat_name = "Category:AI-generated media" #category to check

# save output
with open("files.txt", "w", encoding="utf-8") as output_file:
    process_cat(cat_name, output_file=output_file)