Last active
November 16, 2018 17:23
-
-
Save salmanmaq/b908ed1fe946e492dfd7679c695ae37f to your computer and use it in GitHub Desktop.
Get a list of arXiv identifiers of Core and Non-Core records in INSPIRE
This file contains hidden or 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
| """ | |
| Get the arxiv ids of all the Core and Non-Core records in INSPIRE. | |
| """ | |
| from invenio_search import current_search_client as es | |
| from elasticsearch.helpers import scan | |
| import numpy as np | |
| core = [] | |
| non_core = [] | |
| for hit in scan(es, query={"query": {"exists": {"field": "arxiv_eprints"}}, "_source": ["core", "arxiv_eprints"]}, index='records-hep', doc_type='hep'): | |
| source = hit['_source'] | |
| if source.get('core') == True: | |
| core.append(source['arxiv_eprints'][0]['value']) | |
| else: | |
| non_core.append(source['arxiv_eprints'][0]['value']) | |
| core = np.array(core) | |
| non_core = np.array(non_core) | |
| core.tofile('inspire_core_list.txt', sep='\n') | |
| non_core.tofile('inspire_noncore_list.txt', sep='\n') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment