def get_bib(self,EID=None):
EID = int(EID)
scp_doc = AbsDoc(scp_id = EID)
scp_doc.read(self.client)
scp_doc.write()
bib=[]
for x in scp_doc.data.get('item').get('bibrecord').get('tail').get('bibliography').get('reference'):
EID_x = x.get('ref-info').get('refd-itemidlist').get('itemid')[1].get('$')
bib.append(EID_x)
return bib
def scopus_abs(scopus_id=None):
## Scopus (Abtract) document example
# Initialize document with ID as integer
scp_doc = AbsDoc(scp_id=scopus_id)
if scp_doc.read(client):
print("scp_doc.title: ", scp_doc.title)
scp_doc.write()
def readAbsDocWithScopusID(self, scpID='84872135457'):
## Scopus (Abtract) document example
# Initialize document with Scopus ID.
scp_doc = AbsDoc(scp_id=scpID)
if scp_doc.read(self.client):
print("scp_doc.title: ", scp_doc.title)
scp_doc.write()
else:
print("Read document failed.")
def autorships(dataset_name, aut_dump_name):
data = pd.read_csv(dataset_name)
ids = data['scopusID'].values
with open(aut_dump_name, 'w') as aut:
num = 0
for id in tqdm(ids):
scp_doc = AbsDoc(scp_id=id.split(':')[1])
if scp_doc.read(client):
scp_doc.write()
else:
print("Read document failed.")
aut.write('None' + u'\r\n')
continue
num += 1
try:
aut.write(';'.join([':'.join([i['ce:indexed-name'], i['@auid']])
for i in scp_doc.data['authors']['author']]) + u'\r\n')
except:
aut.write('None' + u'\r\n')
else:
print ("Read author failed.")
## Affiliation example
# Initialize affiliation with ID as string
my_aff = ElsAffil(affil_id = '60101411')
if my_aff.read(client):
print ("my_aff.name: ", my_aff.name)
my_aff.write()
else:
print ("Read affiliation failed.")
## Scopus (Abtract) document example
# Initialize document with ID as integer
scp_doc = AbsDoc(scp_id = 84872135457)
if scp_doc.read(client):
print ("scp_doc.title: ", scp_doc.title)
scp_doc.write()
else:
print ("Read document failed.")
## ScienceDirect (full-text) document example using PII
pii_doc = FullDoc(sd_pii = 'S1674927814000082')
if pii_doc.read(client):
print ("pii_doc.title: ", pii_doc.title)
pii_doc.write()
else:
print ("Read document failed.")
## ScienceDirect (full-text) document example using DOI
doi_doc = FullDoc(doi = '10.1016/S1525-1578(10)60571-5')
def genData(self):
raw_df = self.raw_df
scopus_list = raw_df['scopus']
# Load configuration
con_file = open("config.json")
config = json.load(con_file)
con_file.close()
# Initialize client
client = ElsClient(config['apikey'])
author_id_list = []
given_name_list = []
sur_name_list = []
affiliation_id_list = []
affiliation_city_list = []
affilname_list = []
affiliation_country_list = []
citedby_count_list = []
for scopus_id in scopus_list:
print(len(author_id_list))
# Initialize document with Scopus ID.
print(scopus_id)
if type(scopus_id) is str:
scopus_id = self.scopusID(scopus_id)
# ['client', 'data', 'id', 'int_id', 'read', 'title', 'uri', 'write']
scp_doc = AbsDoc(scp_id=scopus_id)
if scp_doc.read(client):
# dict_keys(['coredata'])
# dict_keys(['srctype', 'prism:issueIdentifier', 'eid', 'prism:coverDate', 'prism:aggregationType', 'prism:url', 'subtypeDescription', 'dc:creator', 'link', 'prism:publicationName', 'source-id', 'citedby-count', 'prism:volume', 'subtype', 'prism:pageRange', 'dc:title', 'prism:endingPage', 'openaccess', 'openaccessFlag', 'prism:doi', 'prism:issn', 'prism:startingPage', 'dc:identifier'])
# dict_keys(['ce:given-name', 'preferred-name', '@seq', 'ce:initials', '@_fa', 'affiliation', 'ce:surname', '@auid', 'author-url', 'ce:indexed-name'])
if 'dc:creator' in scp_doc.data['coredata'].keys():
if 'ce:given-name' in scp_doc.data['coredata'][
'dc:creator']['author'][0].keys():
given_name_list.append(
scp_doc.data['coredata']['dc:creator']
['author'][0]['ce:given-name'])
else:
given_name_list.append(
scp_doc.data['coredata']['dc:creator']
['author'][0]['preferred-name']
['ce:given-name'])
if 'affiliation' in scp_doc.data['coredata'][
'dc:creator']['author'][0].keys():
# print(type(scp_doc.data['coredata']['dc:creator']['author'][0]['affiliation']))
if type(scp_doc.data['coredata']['dc:creator']
['author'][0]['affiliation']) is list:
affiliation_id_list.append(
scp_doc.data['coredata']['dc:creator']
['author'][0]['affiliation'][0]['@id'])
else:
affiliation_id_list.append(
scp_doc.data['coredata']['dc:creator']
['author'][0]['affiliation']['@id'])
else:
affiliation_id_list.append('NA')
author_id_list.append(
scp_doc.data['coredata']['dc:creator']['author'][0]
['@auid'])
sur_name_list.append(
scp_doc.data['coredata']['dc:creator']['author'][0]
['ce:surname'])
else:
given_name_list.append('NA')
sur_name_list.append('NA')
author_id_list.append('NA')
affiliation_id_list.append('NA')
citedby_count_list.append(
scp_doc.data['coredata']['citedby-count'])
else:
given_name_list.append('NA')
sur_name_list.append('NA')
author_id_list.append('NA')
affiliation_id_list.append('NA')
citedby_count_list.append('NA')
else:
given_name_list.append('NA')
sur_name_list.append('NA')
author_id_list.append('NA')
affiliation_id_list.append('NA')
citedby_count_list.append('NA')
raw_df['given-name'] = given_name_list
raw_df['sur_name'] = sur_name_list
raw_df['author_id'] = author_id_list
raw_df['affiliation_id'] = affiliation_id_list
raw_df['citedby_count'] = citedby_count_list
return raw_df