Simple script for multithreaded downloading from archive.org

download_from_internet_archive.py

"""
BSD Zero Clause License

Copyright (c) 2023 Wu Tingfeng

Permission to use, copy, modify, and/or distribute this software for any
purpose with or without fee is hereby granted.

THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
"""
# pip install internetarchive
from internetarchive import download

import concurrent.futures

# archive.org raw link format
# https://archive.org/details/{identifier}

# Replace the below raw_links with the
# archive.org collections that you want to download

raw_links = """
https://archive.org/details/nasa
https://archive.org/details/goodytwoshoes00newyiala
"""

links = [l.strip() for l in raw_links.split("\n") if l.strip()]
identifiers = [l.replace("https://archive.org/details/", "") for l in links]

with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
    future_to_identifier = {
        executor.submit(
            download, identifier, **{"verbose": True, "checksum": True}
        ): identifier
        for identifier in identifiers
    }
    for future in concurrent.futures.as_completed(future_to_identifier):
        identifier = future_to_identifier[future]
        try:
            future.result()
        except Exception as exc:
            print("%r generated an exception: %s" % (identifier, exc))
        else:
            print("%r is successful" % identifier)