Simple script to download MARCXML and PDFs from the internet archive

ia_download.py

#!/usr/bin/env python
import os, sys

ids = open(sys.argv[1])

for id in ids:
    id = id.strip()
    pdf_cmd = "wget http://archive.org/download/%s/%s.pdf" % (id, id)
    marc_cmd = "wget http://archive.org/download/%s/%s_archive_marc.xml" % (id, id)

    os.system(pdf_cmd)
    os.system(marc_cmd)