import hashlib

import os

import re

from urllib.parse import urlparse

def invalidate_cache(url, staging_envs, cache_dir="cache"):

"""

Invalidates the cache for a given URL if it's in a staging environment.

Args:

url (str): The URL of the HTML document.

staging_envs (list): A list of staging environment names (e.g., ["staging", "dev"]).

cache_dir (str): The directory where the cache is stored.

"""

if not isinstance(url, str):

raise TypeError("URL must be a string.")

if not isinstance(staging_envs, list):

raise TypeError("staging_envs must be a list.")

if not all(isinstance(env, str) for env in staging_envs):

raise TypeError("All elements in staging_envs must be strings.")

if not os.path.exists(cache_dir):

os.makedirs(cache_dir)

try:

parsed_url = urlparse(url)

filename = parsed_url.path

if not filename:

filename = "index.html" # Default filename

# Generate a hash of the URL for cache key

cache_key = hashlib.md5(filename.encode('utf-8')).hexdigest()

cache_file_path = os.path.join(cache_dir, cache_key)

# Check if the cache file exists

if os.path.exists(cache_file_path):

# Check if the URL is in a staging environment

if any(env in url.lower() for env in staging_envs):

# Invalidate the cache by deleting the file

os.remove(cache_file_path)

print(f"Invalidated cache for: {url}")

else:

print(f"Cache valid for: {url}")

else:

print(f"Cache file not found for: {url}")

except Exception as e:

print(f"Error processing URL {url}: {e}")

if __name__ == '__main__':

#Example Usage

invalidate_cache("https://staging.example.com/index.html", ["staging"])

invalidate_cache("https://dev.example.com/about.html", ["dev"])

invalidate_cache("https://example.com/contact.html", ["staging", "dev"])

invalidate_cache("https://example.com/index.html") #Normal environment

invalidate_cache(123) #Test input validation