diff --git a/1-enrich-with-datacite/concatenate-enrich-dois.py b/1-enrich-with-datacite/concatenate-enrich-dois.py index 08f452912804cbc54fd54af5c63790876f027049..7a0e8b134c4a528b7cd0560e9e06b51a1f759477 100644 --- a/1-enrich-with-datacite/concatenate-enrich-dois.py +++ b/1-enrich-with-datacite/concatenate-enrich-dois.py @@ -61,6 +61,21 @@ if temp_rows : ## output another csv with datacite client and number of datasets df_client_raw = df_out["client"].value_counts() + + ## get informations about each client + client_names = [] + client_years = [] + client_urls = [] + for client in df_client_raw["client"]: + req = requests.get('https://api.datacite.org/clients?query=id:%22cern.zenodo%22') + client_names.append(req.json()["data"][0]["attributes"]["name"]) + client_years.append(req.json()["data"][0]["attributes"]["year"]) + client_urls.append(req.json()["data"][0]["attributes"]["url"]) + + ## add informations to the output csv + df_client_raw["name"] = client_names + df_client_raw["year"] = client_years + df_client_raw["url"] = client_urls df_client_raw.to_csv("all_datacite_clients_for_uga.csv")