A script to download all (as of April 2018) newspaper articles from Papers Past (NZ)

paperspast_all.py

import requests

number = 1

# Note, this will take a long time!
while number < 1318493:
        
    # Make sure to change your API key at the end of the URL
    urltext = "http://api.digitalnz.org/v3/records.xml?api_key=################&and[collection][]=Papers+Past&sort=date&text=+&and[category][]=Newspapers&direction=asc&page=" + str(number)
    
    response = requests.get(urltext)
    newtext = response.text
    data = newtext.encode('ascii', 'ignore').decode('ascii')
    with open('ppnewspapers\\' + str(number) + '.xml', 'w') as f:
        f.write(data)
    print(str((number*20)-19) + "-" + str(number*20) + " out of " + str(26369857) + " collected\n")
    number = number+1