Created
February 11, 2019 10:48
-
-
Save alaniwi/f5ab883275ca416fd2bd69ada01e4334 to your computer and use it in GitHub Desktop.
Script to get a list of dataset IDs from the index node via the ESGF search.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Gets a list of dataset IDs from the index node via the ESGF search. | |
""" | |
import requests | |
class GetSolrIDs(object): | |
def __init__(self, | |
url='https://c3s-models-index.ceda.ac.uk/esg-search/search/', | |
data_node='data.mips.copernicus-climate.eu', | |
verbose=False): | |
self.url = url | |
self.data_node = data_node | |
self.verbose = verbose | |
def _get_ids_page(self, start, count): | |
if self.verbose: | |
print("querying with start={}".format(start)) | |
field = 'instance_id' | |
params = {'offset': start, | |
'limit': count, | |
'type': 'Dataset', | |
'data_node': self.data_node, | |
'format': 'application/solr+json', | |
'fields': field} | |
resp = requests.get(self.url, params=params) | |
content = resp.json() | |
return [doc[field] for doc in content["response"]["docs"]] | |
def get_ids(self, num_per_request=10000): | |
all_ids = [] | |
start = 0 | |
while True: | |
ids = self._get_ids_page(start, num_per_request) | |
if not ids: | |
return all_ids | |
all_ids.extend(ids) | |
start += num_per_request | |
def main(): | |
getter = GetSolrIDs() | |
ids = getter.get_ids() | |
for id in sorted(ids): | |
print(id) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Needs
requests
.