archiveit-covid19.py

#!/usr/bin/env python3

import csv
import requests

url = 'https://partner.archive-it.org/api/seed'
params = {
    "collection": 13529,
    "limit": 100,
    "offset": 0
}

out = csv.writer(open('archiveit-covid19.csv', 'w'))
out.writerow(['Url', 'Title', 'Last Update'])

while True:
    resp = requests.get(url, params=params)
    seeds = resp.json()
    if len(seeds) == 0: break

    for seed in seeds:

        if "Title" in seed["metadata"]:
            title = seed["metadata"]["Title"][0]["value"]
        else:
            title = ""

        out.writerow([
            seed['url'],
            title,
            seed["last_updated_date"]
        ])

    params['offset'] += 100