Created
December 24, 2022 17:21
-
-
Save Brandon-Rozek/bc850da353a3531e91348068035475fb to your computer and use it in GitHub Desktop.
Script that takes a URL and requests the Internet Archive to snapshot it.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/env python | |
from argparse import ArgumentParser | |
from urllib import request | |
from urllib.parse import urlparse | |
import sys | |
parser = ArgumentParser(description="Request Internet Archive to save the site") | |
parser.add_argument("URL", type=str, help="URL to save") | |
parser.add_argument("-s", action='store_true', help="Silent. Makes output less verbose") | |
args = vars(parser.parse_args()) | |
INPUT_URL = args['URL'] | |
SILENT = args.get('s') | |
# Remove scheme from URL | |
parsed_url = urlparse(INPUT_URL) | |
scheme = f"{parsed_url.scheme}://" | |
save_url = parsed_url.geturl().replace(scheme, "", 1) | |
try: | |
if not SILENT: | |
print("Sending request to the internet archive...") | |
response = request.urlopen(f"https://web.archive.org/save/{save_url}") | |
if not SILENT: | |
print("Archive Link:", response.url) | |
else: | |
print(response.url) | |
except Exception as e: | |
print(e) | |
print("Failed to save to the Internet Archive") | |
sys.exit(1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment