Pulls down Digital Commonwealth identifiers from a search URL and prints to stdout.
Grab a URL generated from the DC search portal, and pass as the first argument to the script. Pipe the output to whatever file you want.
python3 identifier-puller.py "https://collections.leventhalmap.org/search?utf8=✓&q=bromley" > bromleys.txt
| #!/usr/bin/env python3 | |
| import requests | |
| import json | |
| import argparse | |
| def processResultsPage(resultsPageJSON): | |
| identifiers = [] | |
| for doc in resultsPageJSON['response']['docs']: | |
| identifiers.append(doc['id']) | |
| if not resultsPageJSON['response']['pages']['last_page?']: | |
| p = resultsPageJSON['response']['pages']['next_page'] | |
| r = requests.get('{}{}{}'.format( searchURL.replace("/search?","/search.json?"), "&per_page=500&page=", p)) | |
| processResultsPage( r.json() ) | |
| else: | |
| pass | |
| return identifiers | |
| def main(): | |
| parser = argparse.ArgumentParser(description='pull identifiers for an lmec digital collections search') | |
| parser.add_argument('searchURL', metavar='SEARCH_URL', type=str, help='Fully qualified search url, e.g. https://collections.leventhalmap.org/search?utf8=✓&q=bromley') | |
| args = parser.parse_args() | |
| identifiersList = [] | |
| searchURL = args.searchURL | |
| r = requests.get('{}{}'.format( searchURL.replace("/search?","/search.json?"), "&per_page=500")) | |
| identifiers = processResultsPage( r.json() ) | |
| for identifier in identifiers: | |
| print(identifier) | |
| if __name__ == '__main__': | |
| main() |