# Initialize author with uri
URI = "https://krr.cs.vu.nl/"
data = {"data": "24.3"}
data_json = json.dumps(data)
headers = {'Accept': 'application/json'}
my_auth = ElsAuthor(
uri='https://api.elsevier.com/content/author/author_id/7004322609')
#data from Elsevier
# resp = client.exec_request('https://api.elsevier.com/content/search/scopus?query=all(7004322609)&apiKey=ff61921fc97787106a446daa9dc3827b')
resp = client.exec_request(
'https://api.elsevier.com/content/search/author?query=authlast(Harmelen)&apiKey=7f59af901d2d86f78a1fd60c1bf9426a'
)
data = resp #data from scopus
#data from JSON file
# with open('data_scopus_author.json') as json_file:
# data_json_file = json.load(json_file)
# data = data_json_file #data from JSON file
with open('data_scopus_author.json', 'w') as outfile:
json.dump(resp, outfile)
pprint.pprint(data)
class ElsevierSearcher:
__base_url = u'https://api.elsevier.com/content/search/'
__api_key = u'e7882eed968063f188d6c53a919528a7'
def __init__(self, index: str, apikey: str = __api_key):
self.articles_found = []
self.apikey = apikey
self.index = index
self.els_client = ElsClient(self.apikey)
self._uri = self.__base_url + index + '?'
def search(self,
queryterms: list = None,
start_year: int = None,
end_year: int = None,
content_type: str = 'journals',
start_record: int = None,
sort_field: str = None,
sort_order: int = None,
max_records: int = None,
article_title: str = None,
author: list = None,
journal: list = None):
"""
@param queryterms: list of lists. Terms within the same list are
separated by an OR. Lists are separated by an AND
@param search_type: meta_data or querytext.
meta_data: This field enables a free-text search of all
configured metadata fields and the abstract. Accepts
complex queries involving field names and boolean
operators.
querytext: This field enables a free-text search of all
configured metadata fields, abstract and document text.
Accepts complex queries involving field names and boolean
operators.
@param start_year: Start value of Publication Year to restrict results by.
@param end_year: End value of Publication Year to restrict results by.
@param content_type: Note: these are case sensitive and must be spelled as
presented here to get a result: Journals, Conference, Early Access,
Standards, Books, Courses
@param start_record: Sequence number of first record to fetch. Default: 1
@param sort_field: Field name on which to sort. Choose from: article_number
article_title, author, publication_title, publication_year
@param sort_order: asc (for ascending sort) or desc (for descending sort)
@param max_records: The number of records to fetch. Maximum: 200
@return the data fields returned by the search are described by the
following link https://developer.ieee.org/docs/read/Metadata_API_responses
"""
formated_query = ''
if self.index == 'scopus':
formated_query = "TITLE-ABS-KEY(("
if self.index == 'scidir':
formated_query = "tak(("
for index_group, group in enumerate(queryterms):
if index_group > 0:
formated_query += ' AND ('
# else:
# # formated_query += '('
for index_term, term in enumerate(group):
if index_term > 0:
formated_query += ' OR '
formated_query += f'"{term}"'
if (index_term + 1) == len(group):
formated_query += ')'
formated_query += ')'
if author:
str_author = ' AND '.join([f'"{x}"' for x in author])
if self.index == 'scopus':
formated_query += f' AND AUTHOR-NAME({str_author})'
if self.index == 'scidir':
formated_query += f' AND aut({str_author})'
if article_title:
if self.index == 'scopus':
formated_query += f' AND TITLE("{article_title}")'
if self.index == 'scidir':
formated_query += f' AND ttl("{article_title}")'
if journal:
str_journal = ' AND '.join([f'"{x}"' for x in journal])
if self.index == 'scopus':
formated_query += f' AND SRCTITLE({str_journal})'
if self.index == 'scidir':
formated_query += f' AND src({str_journal})'
query_params = dict()
print(formated_query)
query_params['query'] = formated_query
# query_params['view'] = 'STANDARD'
if start_year:
start_year = str(start_year)
date = start_year
if end_year:
end_year = str(end_year)
date += f'-{end_year}'
query_params['date'] = date
if content_type:
query_params['content'] = content_type
if start_record:
query_params['start'] = start_record
if max_records:
query_params['count'] = max_records
get_all = True
url = self._uri + urlencode(query_params, quote_via=quote_plus)
print(url)
self._api_response = self.els_client.exec_request(url)
self._tot_num_res = int(
self._api_response['search-results']['opensearch:totalResults'])
self.results = self._api_response['search-results']['entry']
print("a request completed...")
if get_all is True:
while (len(self.results) < self._tot_num_res) and (len(
self.results) < 5000):
for e in self._api_response['search-results']['link']:
if e['@ref'] == 'next':
next_url = e['@href']
self._api_response = self.els_client.exec_request(next_url)
self.results += self._api_response['search-results']['entry']
print("a request completed...")
return self.results
client = ElsClient(config['apikey'])
# client.inst_token = config['insttoken']
## Author example
# Initialize author with uri
data = {"data" : "24.3"}
data_json = json.dumps(data)
headers = {'Accept': 'application/json'}
my_auth = ElsAuthor(
uri = 'https://api.elsevier.com/content/author/author_id/7004322609')
resp = client.exec_request('https://api.elsevier.com/content/author/author_id/7004322609?apiKey=2af6a3b4ba3f250031381ec4c63c1c5e')
import pprint
pprint.pprint(resp)
# print("Scopus")
# #ID of the Author?
# print("Personal ID: " + resp['author-retrieval-response'][0]['author-profile']['affiliation-current']['affiliation']['@affiliation-id'])
# #different kind of names used
# print(resp['author-retrieval-response'][0]['author-profile']['name-variant'])
# #preferred-name
# print(resp['author-retrieval-response'][0]['author-profile']['preferred-name'])
# #Author ID
# print(resp['author-retrieval-response'][0]['coredata']['dc:identifier'])
# #Total document-count
has_scopus_id = transformToRDF('hasScopusID')
has_description = transformToRDF('hasDescription')
has_isbn = transformToRDF('hasISBN')
has_issn = transformToRDF('hasISSN')
has_publication_name = transformToRDF('hasPublicationName')
has_page_range = transformToRDF('hasPageRange')
has_publication_year = transformToRDF('hasPublicationYear')
has_doi = transformToRDF('hasDoi')
for doi in doi_list:
print(doi)
#data from Elsevier
url = 'https://api.elsevier.com/content/abstract/doi/'+ doi +'?apiKey=ff61921fc97787106a446daa9dc3827b'
resp = client.exec_request(url)
data = resp
#=======================
# Publications
#=======================
#Title
if 'dc:title' in data['abstracts-retrieval-response']['coredata']:
title_pub = transformToRDF(data['abstracts-retrieval-response']['coredata']['dc:title'])
titles = transformToRDF('Titles')
g.add((titles, RDF.type, OWL.Class))
g.add((titles, RDFS.label, title_pub))
g.add((titles, RDFS.subClassOf, OWL.Thing))
g.add((title_pub, RDF.type, FOAF.Document))
