def __init__(self, author):
"""author should be an xml element.
The following attributes are supported:
author
indexed_name
given_name
surname
initials
author_url - the scopus api url to get more information
auid - the scopus id for the author
scopusid - the scopus id for the author
seq - the index of the author in the author list.
affiliations - a list of ScopusAuthorAffiliation objects
This class is not the same as the one in scopus.scopus_author, which
uses the scopus author api.
"""
self.author = author
self.indexed_name = get_encoded_text(author, 'ce:indexed-name')
self.given_name = get_encoded_text(author, 'ce:given-name')
self.surname = get_encoded_text(author, 'ce:surname')
self.initials = get_encoded_text(author, 'ce:initials')
self.author_url = get_encoded_text(author, 'dtd:author-url')
self.auid = author.attrib.get('auid', None)
self.scopusid = self.auid
self.seq = author.attrib.get('seq', None)
self.affiliations = [
_ScopusAuthorAffiliation(aff)
for aff in author.findall('dtd:affiliation', ns)
]
def __init__(self, author):
"""author should be an xml element.
The following attributes are supported:
author
indexed_name
given_name
surname
initials
author_url - the scopus api url to get more information
auid - the scopus id for the author
scopusid - the scopus id for the author
seq - the index of the author in the author list.
affiliations - a list of ScopusAuthorAffiliation objects
This class is not the same as the one in scopus.scopus_author, which
uses the scopus author api.
"""
self.author = author
self.indexed_name = get_encoded_text(author, 'ce:indexed-name')
self.given_name = get_encoded_text(author, 'ce:given-name')
self.surname = get_encoded_text(author, 'ce:surname')
self.initials = get_encoded_text(author, 'ce:initials')
self.author_url = get_encoded_text(author, 'author-url')
self.auid = author.attrib.get('auid')
self.scopusid = self.auid
self.seq = author.attrib.get('seq')
self.affiliations = [_ScopusAuthorAffiliation(aff)
for aff in author.findall('affiliation', ns)]
def name(self):
"""Author name."""
return ((get_encoded_text(self.xml,
'author-profile/preferred-name/given-name') or '') +
' ' +
(get_encoded_text(self.xml,
'author-profile/preferred-name/surname') or ''))
def name(self):
"""Author name."""
return ((get_encoded_text(self.xml,
'author-profile/preferred-name/given-name') or '') +
' ' +
(get_encoded_text(self.xml,
'author-profile/preferred-name/surname') or ''))
def __init__(self, affiliation):
"""affiliation should be an xml element from the main abstract"""
self.affiliation = affiliation
self.affilname = get_encoded_text(affiliation, 'affilname')
self.city = get_encoded_text(affiliation, 'affiliation-city')
self.country = get_encoded_text(affiliation, 'affiliation-country')
self.href = affiliation.attrib.get('href', None)
self.id = affiliation.attrib.get('id', None)
def __init__(self, affiliation):
"""affiliation should be an xml element from the main abstract"""
self.affiliation = affiliation
self.affilname = get_encoded_text(affiliation, 'affilname')
self.city = get_encoded_text(affiliation, 'affiliation-city')
self.country = get_encoded_text(affiliation, 'affiliation-country')
self.href = affiliation.attrib.get('href', None)
self.id = affiliation.attrib.get('id', None)
def __init__(self, aff_id, refresh=False):
"""Class to represent an Affiliation in Scopus.
Parameters
----------
aff_id : str or int
The Scopus Affiliation ID.
refresh : bool (optional, default=False)
Whether to refresh the cached file if it exists or not.
Notes
-----
The files are cached in ~/.scopus/affiliation/{aff_id}.
"""
self._affiliation_id = aff_id
qfile = os.path.join(SCOPUS_AFFILIATION_DIR, str(aff_id))
url = ('http://api.elsevier.com/content/affiliation/'
'affiliation_id/{}'.format(aff_id))
xml = ET.fromstring(get_content(qfile, url=url, refresh=refresh))
# public url
self._url = xml.find('coredata/link[@rel="scopus-affiliation"]')
if self._url is not None:
self._url = self.url.get('href')
self.api_url = get_encoded_text(xml, 'coredata/prism:url')
self._nauthors = get_encoded_text(xml, 'coredata/author-count')
self._ndocuments = get_encoded_text(xml, 'coredata/document-count')
self._name = get_encoded_text(xml, 'affiliation-name')
self._address = get_encoded_text(xml, 'address')
self._city = get_encoded_text(xml, 'city')
self._country = get_encoded_text(xml, 'country')
def get_coauthors(self):
"""Return list of coauthors, their scopus-id and research areas."""
url = self.xml.find('coredata/link[@rel="coauthor-search"]').get(
'href')
xml = download(url=url).text.encode('utf-8')
xml = ET.fromstring(xml)
coauthors = []
N = int(get_encoded_text(xml, 'opensearch:totalResults') or 0)
AUTHOR = namedtuple('Author',
['name', 'scopus_id', 'affiliation', 'categories'])
count = 0
while count < N:
params = {'start': count, 'count': 25}
xml = download(url=url, params=params).text.encode('utf-8')
xml = ET.fromstring(xml)
for entry in xml.findall('atom:entry', ns):
given_name = get_encoded_text(
entry, 'atom:preferred-name/atom:given-name')
surname = get_encoded_text(entry,
'atom:preferred-name/atom:surname')
coauthor_name = '{0} {1}'.format(given_name, surname)
scopus_id = get_encoded_text(entry, 'dc:identifier').replace(
'AUTHOR_ID:', '')
affiliation = get_encoded_text(
entry, 'atom:affiliation-current/atom:affiliation-name')
# get categories for this author
s = ', '.join([
'{0} ({1})'.format(subject.text,
subject.attrib['frequency'])
for subject in entry.findall('atom:subject-area', ns)
])
coauthors += [AUTHOR(coauthor_name, scopus_id, affiliation, s)]
count += 25
return coauthors
def get_coauthors(self):
"""Return list of coauthors, their scopus-id and research areas."""
url = self.xml.find('coredata/link[@rel="coauthor-search"]').get('href')
xml = download(url=url).text.encode('utf-8')
xml = ET.fromstring(xml)
coauthors = []
N = int(get_encoded_text(xml, 'opensearch:totalResults') or 0)
AUTHOR = namedtuple('Author',
['name', 'scopus_id', 'affiliation', 'categories'])
count = 0
while count < N:
params = {'start': count, 'count': 25}
xml = download(url=url, params=params).text.encode('utf-8')
xml = ET.fromstring(xml)
for entry in xml.findall('atom:entry', ns):
given_name = get_encoded_text(entry,
'atom:preferred-name/atom:given-name')
surname = get_encoded_text(entry,
'atom:preferred-name/atom:surname')
coauthor_name = u'{0} {1}'.format(given_name, surname)
scopus_id = get_encoded_text(entry,
'dc:identifier').replace('AUTHOR_ID:', '')
affiliation = get_encoded_text(entry,
'atom:affiliation-current/atom:affiliation-name')
# get categories for this author
s = u', '.join(['{0} ({1})'.format(subject.text,
subject.attrib['frequency'])
for subject in
entry.findall('atom:subject-area', ns)])
coauthors += [AUTHOR(coauthor_name, scopus_id, affiliation, s)]
count += 25
return coauthors
def orcid(self):
"""The author's ORCID."""
return get_encoded_text(self.xml, 'coredata/orcid')
def org_url(self):
"""Website of the affiliation."""
return get_encoded_text(self.xml, 'institution-profile/org-URL')
def org_type(self):
"""Type of the affiliation (only present if profile is org profile)."""
return get_encoded_text(self.xml, 'institution-profile/org-type')
def ndocuments(self):
"""Number of documents for the affiliation."""
return get_encoded_text(self.xml, 'coredata/document-count')
def coverDate(self):
"""The date of the cover the abstract is in."""
return get_encoded_text(self.coredata, 'prism:coverDate')
def city(self):
"""The city of the affiliation."""
return get_encoded_text(self.xml, 'city')
def org_domain(self):
"""Internet domain of the affiliation."""
return get_encoded_text(self.xml, 'institution-profile/org-domain')
def firstname(self):
"""Author first name."""
return (get_encoded_text(self.xml,
'author-profile/preferred-name/given-name') or '')
def current_affiliation(self):
"""Current affiliation according to scopus."""
return get_encoded_text(self.xml, 'author-profile/affiliation-current/'
'affiliation/ip-doc/afdispname')
def ncoauthors(self):
"""Total number of coauthors."""
ncoauthors = get_encoded_text(self.xml, 'coauthor-count')
return int(ncoauthors) if ncoauthors is not None else 0
def citation_count(self):
"""Total number of citing items."""
citation_count = get_encoded_text(self.xml, 'coredata/citation-count')
return int(citation_count) if citation_count is not None else 0
def ncited_by(self):
"""Total number of citing authors."""
ncited_by = get_encoded_text(self.xml, 'coredata/cited-by-count')
return int(ncited_by) if ncited_by is not None else 0
def ndocuments(self):
"""Number of documents authored (excludes book chapters and notes)."""
ndocuments = get_encoded_text(self.xml, 'coredata/document-count')
return int(ndocuments) if ndocuments is not None else 0
def hindex(self):
"""The author hindex"""
hindex = get_encoded_text(self.xml, 'h-index')
return int(hindex) if hindex is not None else 0
def citedby_count(self):
"""Number of articles citing the abstract."""
return int(get_encoded_text(self.coredata, 'citedby-count'))
def api_url(self):
"""URL to the affiliation's API page."""
return get_encoded_text(self.xml, 'coredata/prism:url')
def lastname(self):
"""Author last name."""
return (get_encoded_text(self.xml,
'author-profile/preferred-name/surname') or '')
def name(self):
"""The name of the affiliation."""
return get_encoded_text(self.xml, 'affiliation-name')
def description(self):
"""Return the description of a record.
Note: If this is empty, try the abstract instead.
"""
return get_encoded_text(self.coredata, 'dc:description')
def country(self):
"""The country of the affiliation."""
return get_encoded_text(self.xml, 'country')
def address(self):
"""The address of the affiliation."""
return get_encoded_text(self.xml, 'address')
def nauthors(self):
"""Number of authors in the affiliation."""
return get_encoded_text(self.xml, 'coredata/author-count')
def state(self):
"""The state (country's administrative sububunit) of the affiliation."""
return get_encoded_text(self.xml, 'state')
def api_url(self):
"""URL to the affiliation's API page."""
return get_encoded_text(self.xml, 'coredata/prism:url')
def __init__(self, author_id, refresh=False, refresh_aff=False, level=1):
"""Class to represent a Scopus Author query by the scopus-id.
Parameters
----------
author_id : str or int
The ID of the author to search for.
refresh : bool (optional, default=False)
Whether to refresh the cached file (if it exists) or not.
refresh_aff : bool (optional, default=False)
Whether to refresh the cached corresponding affiliation views
(if they exist) or not.
level : int (optional, default=1)
Number of * to print in property __str__.
Notes
-----
The files are cached in ~/.scopus/author/{author_id}.
"""
author_id = str(int(author_id))
self.level = level
qfile = os.path.join(SCOPUS_AUTHOR_DIR, author_id)
url = ('http://api.elsevier.com/content/author/'
'author_id/{}').format(author_id)
params = {'author_id': author_id, 'view': 'ENHANCED'}
xml = ET.fromstring(
get_content(qfile, url=url, refresh=refresh, params=params))
self.xml = xml
self._orcid = get_encoded_text(xml, 'coredata/orcid')
hindex = get_encoded_text(xml, 'h-index')
self._hindex = int(hindex) if hindex is not None else 0
ndocuments = get_encoded_text(xml, 'coredata/document-count')
self._ndocuments = int(ndocuments) if ndocuments is not None else 0
_author_id = get_encoded_text(xml, 'coredata/dc:identifier')
self._author_id = _author_id.split(":")[-1]
citation_count = get_encoded_text(xml, 'coredata/citation-count')
self._citation_count = int(
citation_count) if citation_count is not None else 0
ncited_by = get_encoded_text(xml, 'coredata/cited-by-count')
self._ncited_by = int(ncited_by) if ncited_by is not None else 0
ncoauthors = get_encoded_text(xml, 'coauthor-count')
self._ncoauthors = int(ncoauthors) if ncoauthors is not None else 0
self._current_affiliation = get_encoded_text(
xml,
'author-profile/affiliation-current/affiliation/ip-doc/afdispname')
# affiliation history (sort out faulty historic affiliations)
aff_ids = [
el.attrib.get('affiliation-id') for el in xml.findall(
'author-profile/affiliation-history/affiliation')
if el is not None and len(list(el.find("ip-doc").iter())) > 1
]
affs = [
ScopusAffiliation(aff_id, refresh=refresh_aff)
for aff_id in aff_ids
]
self._affiliation_history = affs
date_created = xml.find('author-profile/date-created', ns)
if date_created is not None:
self._date_created = (int(date_created.attrib['year']),
int(date_created.attrib['month']),
int(date_created.attrib['day']))
else:
self._date_created = (None, None, None)
# Research areas
self._area_elements = xml.findall('subject-areas/subject-area')
# {code: name}
d = {int(ae.attrib['code']): ae.text for ae in self._area_elements}
freqs = xml.findall('author-profile/classificationgroup/'
'classifications[@type="ASJC"]/classification')
# {code: frequency}
c = {int(cls.text): int(cls.attrib['frequency']) for cls in freqs}
self._subject_freq = c
categories = [(d[code], c[code]) for code in d]
categories.sort(reverse=True, key=itemgetter(1))
self.categories = categories
self._firstname = (get_encoded_text(
xml, 'author-profile/preferred-name/given-name') or '')
self._lastname = (get_encoded_text(
xml, 'author-profile/preferred-name/surname') or '')
self._name = (
(get_encoded_text(xml, 'author-profile/preferred-name/given-name')
or '') + ' ' +
(get_encoded_text(xml, 'author-profile/preferred-name/surname')
or ''))
# Real website for the author
self._scopus_url = xml.find('coredata/link[@rel="scopus-author"]')
if self._scopus_url is not None:
self._scopus_url = self._scopus_url.get('href')
# API URL for coauthors
self._coauthor_url = xml.find('coredata/link[@rel="coauthor-search"]')
if self._coauthor_url is not None:
self._coauthor_url = self._coauthor_url.get('href')
# Publication history
pub_hist_elements = self.xml.findall('author-profile/journal-history/')
self._pub_hist = pub_hist_elements
def org_domain(self):
"""Internet domain of the affiliation."""
return get_encoded_text(self.xml, 'institution-profile/org-domain')
def __init__(self, EID, view='META_ABS', refresh=False):
"""Class to represent the results from a Scopus abstract.
Parameters
----------
EID : str
The Scopus ID of an abstract.
view : str (optional, default=META_ABS)
The view of the file that should be downloaded. Currently
supported values: META, META_ABS, FULL.
refresh : bool (optional, default=False)
Whether to refresh the cached file if it exists or not.
Notes
-----
The files are cached in ~/.scopus/xml/{eid}.
"""
allowed_views = ('META', 'META_ABS', 'FULL')
if view not in allowed_views:
raise ValueError('view parameter must be one of ' +
', '.join(allowed_views))
# Get file content
qfile = os.path.join(SCOPUS_XML_DIR, EID)
url = "http://api.elsevier.com/content/abstract/eid/{}".format(EID)
params = {'view': view}
xml = ET.fromstring(
get_content(qfile, url=url, refresh=refresh, params=params))
self.xml = xml
if xml.tag == 'service-error':
raise Exception('\n{0}\n{1}'.format(EID, self.xml))
# Parse coredata
coredata = xml.find('dtd:coredata', ns)
self._url = get_encoded_text(coredata, 'prism:url')
self.identifier = get_encoded_text(coredata, 'dc:identifier')
self.eid = get_encoded_text(coredata, 'dtd:eid')
self._doi = get_encoded_text(coredata, 'prism:doi')
self._title = get_encoded_text(coredata, 'dc:title')
self._aggregationType = get_encoded_text(coredata,
'prism:aggregationType')
self._publicationName = get_encoded_text(coredata,
'prism:publicationName')
self._srctype = get_encoded_text(coredata, 'dtd:srctype')
self._citedby_count = get_encoded_text(coredata, 'dtd:citedby-count')
self._publisher = get_encoded_text(coredata, 'dc:publisher')
self._source_id = get_encoded_text(coredata, 'dtd:source-id')
self._issn = get_encoded_text(coredata, 'prism:issn')
self._volume = get_encoded_text(coredata, 'prism:volume')
self._issueIdentifier = get_encoded_text(coredata,
'prism:issueIdentifier')
self._article_number = get_encoded_text(coredata, 'dtd:article-number')
self._startingPage = get_encoded_text(coredata, 'prism:startingPage')
self._endingPage = get_encoded_text(coredata, 'prism:endingPage')
self._pageRange = get_encoded_text(coredata, 'prism:pageRange')
self._coverDate = get_encoded_text(coredata, 'prism:coverDate')
self.creator = get_encoded_text(coredata, 'dc:creator')
self.description = get_encoded_text(coredata, 'dc:description')
sl = coredata.find('dtd:link[@rel="scopus"]', ns).get('href')
self_link = coredata.find('dtd:link[@rel="self"]', ns).get('href')
cite_link = coredata.find('dtd:link[@rel="cited-by"]', ns)
if cite_link:
cite_link = cite_link.get('href')
self.scopus_link = sl
self.self_link = self_link
self.cite_link = cite_link
# Parse subject-areas
subjectAreas = xml.find('dtd:subject-areas', ns)
try:
self._subjectAreas = [a.text for a in subjectAreas]
except:
self._subjectAreas = None
# Parse authors
authors = xml.find('dtd:authors', ns)
self._authors = [_ScopusAuthor(author) for author in authors]
self._affiliations = [
_ScopusAffiliation(aff)
for aff in xml.findall('dtd:affiliation', ns)
]
# Parse items
items = xml.find('item', ns)
self._website = get_encoded_text(
items, 'bibrecord/head/source/website/ce:e-address')
try:
self._citationType = items.find(
'bibrecord/head/citation-info/citation-type').get("code")
except:
self._citationType = None
try:
self._citationLang = items.find(
'bibrecord/head/citation-info/citation-language').get(
"language")
except:
self._citationLang = None
try:
self._references = tail.find('bibrecord/tail/bibliography', ns)
except:
self._references = None
def name(self):
"""The name of the affiliation."""
return get_encoded_text(self.xml, 'affiliation-name')
def author_id(self):
"""The scopus id for the author."""
author_id = get_encoded_text(self.xml, 'coredata/dc:identifier')
return author_id.split(":")[-1]
def city(self):
"""The city of the affiliation."""
return get_encoded_text(self.xml, 'city')
def orcid(self):
"""The author's ORCID."""
return get_encoded_text(self.xml, 'coredata/orcid')
def country(self):
"""The country of the affiliation."""
return get_encoded_text(self.xml, 'country')
def __init__(self, ISSN, refresh=False):
ISSN = str(ISSN)
self.issn = ISSN
qfile = os.path.join(SCOPUS_ISSN_DIR, ISSN)
url = ("http://api.elsevier.com/content/serial/title/issn:" + ISSN)
self.xml = get_content(qfile, refresh, url)
self.publisher = get_encoded_text(self.xml, 'entry/dc:publisher')
self.title = get_encoded_text(self.xml, 'entry/dc:title')
self.aggregationType = get_encoded_text(self.xml,
'entry/prism:aggregationType')
self.prism_url = get_encoded_text(self.xml, 'entry/prism:url')
# Impact factors
SNIP = get_encoded_text(self.xml, 'entry/SNIPList/SNIP')
SNIP_year = self.xml.find('entry/SNIPList/SNIP', ns)
if SNIP_year is not None:
SNIP_year = SNIP_year.get('year')
else:
SNIP_year = -1
IPP = get_encoded_text(self.xml, 'entry/IPPList/IPP')
IPP_year = self.xml.find('entry/IPPList/IPP', ns)
if IPP_year is not None:
IPP_year = IPP_year.get('year')
else:
IPP_year = -1
SJR = get_encoded_text(self.xml, 'entry/SJRList/SJR')
SJR_year = self.xml.find('entry/SJRList/SJR', ns)
if SJR_year is not None:
SJR_year = SJR_year.get('year')
else:
SJR_year = -1
if SNIP:
self.SNIP = float(SNIP)
self.SNIP_year = int(SNIP_year)
else:
self.SNIP = None
self.SNIP_year = None
if IPP:
self.IPP = float(IPP)
self.IPP_year = int(IPP_year)
else:
self.IPP = None
self.IPP_year = None
if SJR:
self.SJR = float(SJR)
self.SJR_year = int(SJR_year)
else:
self.SJR = None
self.SJR_year = None
scopus_url = self.xml.find('entry/link[@ref="scopus-source"]')
if scopus_url is not None:
self.scopus_url = scopus_url.attrib['href']
else:
self.scopus_url = None
homepage = self.xml.find('entry/link[@ref="homepage"]')
if homepage is not None:
self.homepage = homepage.attrib['href']
else:
self.homepage = None
def __str__(self):
"""Return a summary string."""
s = [
'{} {} (updated on {})'.format('*' * self.level, self._name,
time.asctime())
]
url = self.xml.find('coredata/link[@rel="scopus-author"]')
if url is not None:
url = url.get('href', 'None')
else:
url = ''
s += ['']
orcid = get_encoded_text(self.xml, 'coredata/orcid')
if orcid is not None:
s += ['http://orcid.org/' + orcid]
s += [
'{} documents cited {} times by {} people ({} coauthors)'.format(
self._ndocuments, self._citation_count, self._ncited_by,
self._ncoauthors)
]
s += ['#first author papers {0}'.format(self.n_first_author_papers())]
s += ['#last author papers {0}'.format(self.n_last_author_papers())]
s += [
'h-index: {}'.format(self._hindex) + ' AIF(2014) = ' +
'{0:1.2f}'.format(self.author_impact_factor(2015)[2])
]
s += ['Scopus ID created on {}'.format(self.date_created)]
# Current Affiliation. Note this is what Scopus thinks is current.
s += ['\nCurrent affiliation according to Scopus:']
s += [' ' + (self._current_affiliation or '')]
# subject areas
s += ['\nSubject areas']
s += [
textwrap.fill(', '.join(
['{0} ({1})'.format(el[0], el[1]) for el in self.categories]),
initial_indent=' ',
subsequent_indent=' ')
]
# journals published in
temp_s = [el.find('sourcetitle-abbrev').text for el in self._pub_hist]
s += [
'\nPublishes in:\n' + textwrap.fill(
', '.join(temp_s), initial_indent=' ', subsequent_indent=' ')
]
# affiliation history
s += ['\nAffiliation history:']
for aff in self.affiliation_history:
s += [str(aff)]
# print a bibliography
s += [self.get_document_summary()]
return '\n'.join(s)
def nauthors(self):
"""Number of authors in the affiliation."""
return get_encoded_text(self.xml, 'coredata/author-count')
def hindex(self):
"""The author hindex"""
hindex = get_encoded_text(self.xml, 'h-index')
return int(hindex) if hindex is not None else 0
def __init__(self, ISSN, refresh=False):
ISSN = str(ISSN)
self.issn = ISSN
qfile = os.path.join(SCOPUS_ISSN_DIR, ISSN)
url = ("https://api.elsevier.com/content/serial/title/issn:" + ISSN)
self.xml = ET.fromstring(get_content(qfile, refresh, url))
self.publisher = get_encoded_text(self.xml, 'entry/dc:publisher')
self.title = get_encoded_text(self.xml, 'entry/dc:title')
self.aggregationType = get_encoded_text(self.xml,
'entry/prism:aggregationType')
self.prism_url = get_encoded_text(self.xml, 'entry/prism:url')
# Impact factors
SNIP = get_encoded_text(self.xml, 'entry/SNIPList/SNIP')
SNIP_year = self.xml.find('entry/SNIPList/SNIP', ns)
if SNIP_year is not None:
SNIP_year = SNIP_year.get('year')
else:
SNIP_year = -1
IPP = get_encoded_text(self.xml, 'entry/IPPList/IPP')
IPP_year = self.xml.find('entry/IPPList/IPP', ns)
if IPP_year is not None:
IPP_year = IPP_year.get('year')
else:
IPP_year = -1
SJR = get_encoded_text(self.xml, 'entry/SJRList/SJR')
SJR_year = self.xml.find('entry/SJRList/SJR', ns)
if SJR_year is not None:
SJR_year = SJR_year.get('year')
else:
SJR_year = -1
if SNIP:
self.SNIP = float(SNIP)
self.SNIP_year = int(SNIP_year)
else:
self.SNIP = None
self.SNIP_year = None
if IPP:
self.IPP = float(IPP)
self.IPP_year = int(IPP_year)
else:
self.IPP = None
self.IPP_year = None
if SJR:
self.SJR = float(SJR)
self.SJR_year = int(SJR_year)
else:
self.SJR = None
self.SJR_year = None
scopus_url = self.xml.find('entry/link[@ref="scopus-source"]')
if scopus_url is not None:
self.scopus_url = scopus_url.attrib['href']
else:
self.scopus_url = None
homepage = self.xml.find('entry/link[@ref="homepage"]')
if homepage is not None:
self.homepage = homepage.attrib['href']
else:
self.homepage = None
def affiliation_id(self):
"""The Scopus ID of the affiliation."""
return get_encoded_text(self.xml, 'coredata/dc:identifier').split(":")[-1]
def ndocuments(self):
"""Number of documents authored (excludes book chapters and notes)."""
ndocuments = get_encoded_text(self.xml, 'coredata/document-count')
return int(ndocuments) if ndocuments is not None else 0
def ndocuments(self):
"""Number of documents for the affiliation."""
return get_encoded_text(self.xml, 'coredata/document-count')
def ncited_by(self):
"""Total number of citing authors."""
ncited_by = get_encoded_text(self.xml, 'coredata/cited-by-count')
return int(ncited_by) if ncited_by is not None else 0
def org_type(self):
"""Type of the affiliation (only present if profile is org profile)."""
return get_encoded_text(self.xml, 'institution-profile/org-type')
def citation_count(self):
"""Total number of citing items."""
citation_count = get_encoded_text(self.xml, 'coredata/citation-count')
return int(citation_count) if citation_count is not None else 0
def org_url(self):
"""Website of the affiliation."""
return get_encoded_text(self.xml, 'institution-profile/org-URL')
def ncoauthors(self):
"""Total number of coauthors."""
ncoauthors = get_encoded_text(self.xml, 'coauthor-count')
return int(ncoauthors) if ncoauthors is not None else 0
def address(self):
"""The address of the affiliation."""
return get_encoded_text(self.xml, 'address')
def current_affiliation(self):
"""Current affiliation according to scopus."""
return get_encoded_text(
self.xml, 'author-profile/affiliation-current/'
'affiliation/ip-doc/afdispname')
def state(self):
"""The state (country's administrative sububunit) of the affiliation."""
return get_encoded_text(self.xml, 'state')
def firstname(self):
"""Author first name."""
return (get_encoded_text(
self.xml, 'author-profile/preferred-name/given-name') or '')
def __init__(self, aff_id, refresh=False):
"""Class to represent an Affiliation in Scopus.
Parameters
----------
aff_id : str or int
The Scopus Affiliation ID.
refresh : bool (optional, default=False)
Whether to refresh the cached file if it exists or not.
Notes
-----
The files are cached in ~/.scopus/affiliation/{aff_id}.
"""
qfile = os.path.join(SCOPUS_AFFILIATION_DIR, str(aff_id))
url = ('https://api.elsevier.com/content/affiliation/'
'affiliation_id/{}'.format(aff_id))
xml = ET.fromstring(get_content(qfile, url=url, refresh=refresh))
# coredata
self._url = xml.find('coredata/link[@rel="scopus-affiliation"]')
_aff_id = get_encoded_text(xml, 'coredata/dc:identifier')
self._aff_id = _aff_id.split(":")[-1]
if self._url is not None:
self._url = self.url.get('href')
self._api_url = get_encoded_text(xml, 'coredata/prism:url')
self._nauthors = get_encoded_text(xml, 'coredata/author-count')
self._ndocuments = get_encoded_text(xml, 'coredata/document-count')
self._name = get_encoded_text(xml, 'affiliation-name')
self._address = get_encoded_text(xml, 'address')
self._city = get_encoded_text(xml, 'city')
self._country = get_encoded_text(xml, 'country')
# institution-profile
date_created = xml.find('institution-profile/date-created')
if date_created is not None:
self._date_created = (int(date_created.attrib['year']),
int(date_created.attrib['month']),
int(date_created.attrib['day']))
else:
self._date_created = (None, None, None)
self._org_type = get_encoded_text(xml, 'institution-profile/org-type')
self._org_domain = get_encoded_text(xml, 'institution-profile/org-domain')
self._org_url = get_encoded_text(xml, 'institution-profile/org-URL')
def affiliation_id(self):
"""The Scopus ID of the affiliation."""
return get_encoded_text(self.xml,
'coredata/dc:identifier').split(":")[-1]