def get_new_accepteds():
'''Find the new accepted PDFs'''
recid_list = []
for search in SEARCH_ACCEPTED:
search += SEARCH_ACCEPTED_END
recid_list.extend(get_result_ids(search))
result_recids = set(recid_list)
sent_accepteds = retrieve_accepteds()
sent_accepteds_recids = set()
for osti in sent_accepteds:
#sent_recids.add(str(sent[osti][0]))
sent_accepteds_recids.add(sent_accepteds[osti][0])
new_accepteds_recids = list(result_recids - sent_accepteds_recids)
print(f'''
Accepteds {len(result_recids)}
Already sent {len(sent_accepteds_recids)}
New accepteds {len(new_accepteds_recids)}
new_accepteds_recids
{new_accepteds_recids}
''')
if len(new_accepteds_recids) == 0:
return None
jrec_new_accepteds = []
#for recid in new_accepteds_recids[:20]:
for recid in new_accepteds_recids:
jrec_new_accepteds.extend(get_result(recid))
return jrec_new_accepteds
def find_result(search_input=None):
''' Finds records to send email to. '''
if not search_input:
search_input = input('Your search? ').lower()
if len(search_input) > 3:
search = f'{search_input} {SEARCH_FNAL}'
search += f' {SEARCH_DATE}'
if EXCLUDE:
search += f' -{SEARCH_OSTI}'
else:
print('Badly formed search.')
return None
else:
search = search_input
print(search)
result = get_result(search)
if VERBOSE:
print(len(result))
if len(result) > 0:
log = open(LOGFILE, 'a')
date_time_stamp = \
datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
date_time_stamp = date_time_stamp + ' ' + search + ' : '\
+ str(len(result)) + '\n'
log.write(date_time_stamp)
log.close()
return result
print('No result found')
return None
def main(reports):
"""Print the Fermilab report number on a PDF stored at INSPIRE"""
logging.basicConfig(level="INFO")
for report in reports:
done = False
fields = ('arxiv_eprints', 'documents', 'urls')
#print(report)
result = get_result('find r ' + report, fields)
#if len(result):
# print(result)
try:
urls = result[0]['urls']
except (IndexError, KeyError):
try:
eprint = result[0]['arxiv_eprints'][0]['value']
print(report, eprint)
except (IndexError, KeyError):
try:
url = result[0]['documents'][0]['url']
if get_pdf_from_url(url, message=False):
print(report, url)
except (IndexError, KeyError):
pass
continue
for url in urls:
try:
url_desc = url['description']
except KeyError:
print('Problem with:', report)
print(url)
sys.exit()
if url_desc.lower().startswith('fermilab library'):
print(report, 'DONE')
done = True
break
try:
url_value = url['value']
except KeyError:
print('Problem with:', report)
print(url)
sys.exit()
if url_value.lower().endswith('pdf'):
print(report, url_value)
if done:
continue
try:
eprint = result[0]['arxiv_eprints'][0]['value']
print(report, eprint)
continue
except (IndexError, KeyError):
pass
try:
url = result[0]['documents'][0]['url']
print(report, url)
except (IndexError, KeyError):
continue
def get_conference(jrec_hep):
''' Get conference information '''
try:
cnum = jrec_hep['metadata']['publication_info'][0]['cnum']
except KeyError:
return None
search = 'cnum:' + cnum
jrec_confs = get_result(search, fields=None)
if len(jrec_confs) != 1:
return None
jrec_conf = jrec_confs[0]
try:
conference_note = jrec_conf['metadata']['titles'][0]['title']
except KeyError:
conference_note = ''
try:
for item in jrec_conf['metadata']['address']:
if 'cities' in item:
conference_note += ', ' + item['cities'][0]
if 'state' in item:
conference_note += ', ' + item['state']
if 'country_code' in item:
conference_note += ', ' + item['country_code']
except KeyError:
pass
try:
date = jrec_conf['metadata']['opening_date']
#date = get_fieldvalues(recid, "111__x")[0]
date_object = datetime.datetime.strptime(date, '%Y-%m-%d')
date = date_object.strftime('%m/%d')
conference_note += ', ' + date
except KeyError:
pass
try:
date = jrec_conf['metadata']['closing_date']
date_object = datetime.datetime.strptime(date, '%Y-%m-%d')
date = date_object.strftime('%m/%d/%Y')
conference_note += '-' + date
except KeyError:
pass
if conference_note:
return conference_note
return None
def create_xml(osti_id, recid):
"""
The function checks if the OSTI ID should be added to INSPIRE.
If so, it builds up that information.
"""
osti_id = str(osti_id)
recid = str(recid)
recid = recid.replace('oai:inspirehep.net:', '')
search = f'_collections:Fermilab recid:{recid}'
result = get_result(search)
if len(result) == 0:
print(f'No such INSPIRE Fermilab record {recid}')
return None
jrec = result[0]
report = get_fermilab_report(recid)[0]
doi = get_pubnote(jrec)[4]
create_osti_id_pdf(jrec, recid, osti_id, doi, report)
search = '_collections:Fermilab '
search += f'external_system_identifiers.value:{osti_id} '
search += 'external_system_identifiers.schema:osti'
result_osti = get_result_ids(search)
if result_osti == recid:
return None
if len(result_osti) == 1:
print(f'OSTI ID {osti_id} already on {result_osti[0]}')
return None
search = f'recid:{recid} -external_system_identifiers.schema:osti'
if TEST:
print(search)
result = get_result_ids(search)
if len(result) != 1:
print(f'Problem with {recid} {osti_id}')
print(f' {search} {result}')
return False
if TEST:
print(result)
return print_rec(osti_id, recid)
def get_fermilab_report(recid):
'''Get the Fermilab report number.'''
accepted = False
fermilab_report = None
#print(f'recid:{recid}')
result = get_result(search=f'recid:{recid}', fields=('report_numbers', ))
#print(result)
#result = get_record(recid)
#print(result)
try:
#reports = result[0]['metadata']['report_numbers']
reports = result[0]['report_numbers']
except KeyError:
return (fermilab_report, accepted)
for report in reports:
report = report['value'].upper()
if report.startswith('FERMILAB'):
fermilab_report = report
elif report == 'OSTI_ACCEPTED':
accepted = True
#print(fermilab_report, accepted)
return (fermilab_report, accepted)