def references(self):
"""List of namedtuples representing references listed in the abstract,
in the form (position, id, doi, title, authors, sourcetitle,
publicationyear, volume, issue, first, last, text, fulltext).
`position` is the number at which the reference appears in the
document, `id` is the Scopus ID of the referenced abstract (EID
without the "2-s2.0-"), `authors` is a list of the names of the
authors in the format "Surname, Initials", `first` and `last` refer
to the page range, `text` is Scopus-provided information on the
publication and `fulltext` is the text the authors used for
the reference.
Note: Requires the FULL view of the article. Might be empty even if
refcount is positive.
"""
out = []
fields = 'position id doi title authors sourcetitle publicationyear '\
'volume issue first last text fulltext'
ref = namedtuple('Reference', fields)
path = ['item', 'bibrecord', 'tail', 'bibliography', 'reference']
items = listify(chained_get(self._json, path, []))
for item in items:
info = item['ref-info']
volisspag = info.get('ref-volisspag', {})
try:
auth = listify(info['ref-authors']['author'])
authors = [
', '.join([d['ce:surname'], d['ce:initials']])
for d in auth
]
except KeyError: # No authors given
authors = None
ids = listify(info['refd-itemidlist']['itemid'])
try:
doi = [d['$'] for d in ids if d['@idtype'] == 'DOI'][0]
except IndexError:
doi = None
new = ref(position=item.get('@id'),
id=[d['$'] for d in ids if d['@idtype'] == 'SGR'][0],
doi=doi,
authors=authors,
title=info.get('ref-title', {}).get('ref-titletext'),
sourcetitle=info.get('ref-sourcetitle'),
publicationyear=info.get('ref-publicationyear',
{}).get('@first'),
volume=volisspag.get('voliss', {}).get('@volume'),
issue=volisspag.get('voliss', {}).get('@issue'),
first=volisspag.get('pagerange', {}).get('@first'),
last=volisspag.get('pagerange', {}).get('@last'),
text=info.get('ref-text'),
fulltext=item.get('ref-fulltext'))
out.append(new)
return out or None
def sequencebank(self):
"""List of namedtuples representing biological entities defined or
mentioned in the text, in the form (name, sequence_number, type).
"""
path = ['enhancement', 'sequencebanks', 'sequencebank']
items = listify(chained_get(self._head, path, []))
bank = namedtuple('Sequencebank', 'name sequence_number type')
out = []
for item in items:
numbers = listify(item['sequence-number'])
for number in numbers:
new = bank(name=item['@name'], sequence_number=number['$'],
type=number['@type'])
out.append(new)
return out or None
def authors(self):
"""A list of namedtuples representing the article's authors, in the
form (auid, indexed_name, surname, given_name, affiliation_id,
affiliation, city, country).
Note: The affiliation referred to here is what Scopus' algorithm
determined as the main affiliation. Property `authorgroup` provides
all affiliations.
"""
out = []
fields = 'auid indexed_name surname given_name affiliation'
auth = namedtuple('Author', fields)
for item in chained_get(self._json, ['authors', 'author'], []):
affs = [a for a in listify(item.get('affiliation')) if a]
if affs:
aff = [aff.get('@id') for aff in affs]
else:
aff = None
new = auth(auid=item['@auid'],
surname=item.get('ce:surname'),
indexed_name=item.get('ce:indexed-name'),
affiliation=aff,
given_name=chained_get(
item, ['preferred-name', 'ce:given-name']))
out.append(new)
return out or None
def classificationgroup(self):
"""List with (subject group ID, number of documents)-tuples."""
path = ['author-profile', 'classificationgroup', 'classifications',
'classification']
out = [(item['$'], item['@frequency']) for item in
listify(chained_get(self._json, path, []))]
return out or None
def __init__(self, author_id, refresh=False):
"""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. Optionally expressed
as an Elsevier EID (i.e., in the form 9-s2.0-nnnnnnnn).
refresh : bool (optional, default=False)
Whether to refresh the cached file (if it exists) or not.
Notes
-----
The files are cached in ~/.scopus/author_retrieval/{author_id} (without
eventually leading '9-s2.0-').
"""
# Load json
self._id = str(int(str(author_id).split('-')[-1]))
Retrieval.__init__(self, self._id, 'AuthorRetrieval', refresh)
self._json = self._json['author-retrieval-response']
# Checks
try:
self._json = self._json[0]
except KeyError: # Incomplete forward
alias_json = listify(self._json['alias']['prism:url'])
alias = ', '.join([d['$'].split(':')[-1] for d in alias_json])
text = 'Author profile with ID {} has been merged and the main '\
'profile is now one of {}. Please update your records '\
'manually. Functionality of this object is '\
'reduced.'.format(author_id, alias)
warn(text, UserWarning)
def authors(self):
"""A list of namedtuples representing the article's authors, in the
form (auid, indexed_name, surname, given_name, affiliation_id,
affiliation, city, country).
Note: Affiliations listed here are often incomplete and sometimes
use the first author's affiliation for all others. Rather use
property author_group.
"""
out = []
fields = 'auid indexed_name surname given_name affiliation'
auth = namedtuple('Author', fields)
for item in chained_get(self._json, ['authors', 'author'], []):
affs = [a for a in listify(item.get('affiliation')) if a]
if affs:
aff = [aff.get('@id') for aff in affs]
else:
aff = None
new = auth(auid=item['@auid'],
surname=item.get('ce:surname'),
indexed_name=item.get('ce:indexed-name'),
affiliation=aff,
given_name=chained_get(
item, ['preferred-name', 'ce:given-name']))
out.append(new)
return out or None
def __init__(self, author_id, refresh=False):
"""Class to represent a Scopus Author query by the scopus-id.
Parameters
----------
author_id : str or int
The ID of the author to search for. Optionally expressed
as an Elsevier EID (i.e., in the form 9-s2.0-nnnnnnnn).
refresh : bool (optional, default=False)
Whether to refresh the cached file (if it exists) or not.
Notes
-----
The files are cached in ~/.scopus/author_retrieval/{author_id} (without
eventually leading '9-s2.0-').
"""
# Load json
self._id = str(int(str(author_id).split('-')[-1]))
Retrieval.__init__(self, identifier=self._id, api='AuthorRetrieval',
refresh=refresh)
self._json = self._json['author-retrieval-response']
# Checks
try:
self._json = self._json[0]
except KeyError: # Incomplete forward
alias_json = listify(self._json['alias']['prism:url'])
alias = ', '.join([d['$'].split(':')[-1] for d in alias_json])
text = 'Author profile with ID {} has been merged and the main '\
'profile is now one of {}. Please update your records '\
'manually. Functionality of this object is '\
'reduced.'.format(author_id, alias)
warn(text, UserWarning)
def sequencebank(self):
"""List of namedtuples representing biological entities defined or
mentioned in the text, in the form (name, sequence_number, type).
"""
path = ['enhancement', 'sequencebanks', 'sequencebank']
items = listify(chained_get(self._head, path, []))
bank = namedtuple('Sequencebank', 'name sequence_number type')
out = []
for item in items:
numbers = listify(item['sequence-number'])
for number in numbers:
new = bank(name=item['@name'],
sequence_number=number['$'],
type=number['@type'])
out.append(new)
return out or None
def isbn(self):
"""ISBNs belonging to publicationName as tuple of variying length,
(e.g. ISBN-10 or ISBN-13)."""
isbns = listify(chained_get(self._head, ['source', 'isbn'], []))
if len(isbns) == 0:
return None
else:
return tuple((i['$'] for i in isbns))
def isbn(self):
"""ISBNs belonging to publicationName as tuple of variying length,
(e.g. ISBN-10 or ISBN-13)."""
isbns = listify(chained_get(self._head, ['source', 'isbn'], []))
if len(isbns) == 0:
return None
else:
return tuple((i['$'] for i in isbns))
def classificationgroup(self):
"""List with (subject group ID, number of documents)-tuples."""
path = [
'author-profile', 'classificationgroup', 'classifications',
'classification'
]
out = [(item['$'], item['@frequency'])
for item in listify(chained_get(self._json, path, []))]
return out or None
def idxterms(self):
"""List of index terms."""
try:
terms = listify(self._json.get("idxterms", {}).get('mainterm', []))
except AttributeError: # idxterms is empty
return None
try:
return [d['$'] for d in terms]
except AttributeError:
return None
def idxterms(self):
"""List of index terms."""
try:
terms = listify(self._json.get("idxterms", {}).get('mainterm', []))
except AttributeError: # idxterms is empty
return None
try:
return [d['$'] for d in terms]
except AttributeError:
return None
def subject_areas(self):
"""List of namedtuples containing subject areas of the article
in the form ().
Note: Requires the FULL view of the article.
"""
area = namedtuple('Area', 'area abbreviation code')
path = ['subject-areas', 'subject-area']
out = [area(area=item['$'], abbreviation=item['@abbrev'],
code=item['@code'])
for item in listify(chained_get(self._json, path, []))]
return out or None
def chemicals(self):
"""List of namedtuples representing chemical entities in the form
(source, chemical_name, cas_registry_number). In case multiple
numbers given, they are joined on ";".
"""
path = ['enhancement', 'chemicalgroup', 'chemicals']
items = listify(chained_get(self._head, path, []))
chemical = namedtuple('Chemical', 'source chemical_name cas_registry_number')
out = []
for item in items:
for chem in listify(item['chemical']):
number = chem.get('cas-registry-number')
try: # Multiple numbers given
num = ";".join([n['$'] for n in number])
except TypeError:
num = number
new = chemical(source=item['@source'], cas_registry_number=num,
chemical_name=chem['chemical-name'])
out.append(new)
return out or None
def name_variants(self):
"""List of named tuples containing variants of the author name with
number of documents published with that variant.
"""
fields = 'indexed_name initials surname given_name doc_count'
variant = namedtuple('Variant', fields)
path = ['author-profile', 'name-variant']
out = [variant(indexed_name=var['indexed-name'], surname=var['surname'],
doc_count=var.get('@doc-count'), initials=var['initials'],
given_name=var.get('given-name'))
for var in listify(chained_get(self._json, path, []))]
return out or None
def journal_history(self):
"""List of named tuples of authored publications in the form
(sourcetitle, abbreviation, type, issn). issn is only given
for journals. abbreviation and issn may be None.
"""
jour = namedtuple('Journal', 'sourcetitle abbreviation type issn')
path = ['author-profile', 'journal-history', 'journal']
hist = [jour(sourcetitle=pub['sourcetitle'], issn=pub.get('issn'),
abbreviation=pub.get('sourcetitle-abbrev'),
type=pub['@type'])
for pub in listify(chained_get(self._json, path, []))]
return hist or None
def authorgroup(self):
"""A list of namedtuples representing the article's authors organized
by affiliation, in the form (affiliation_id, dptid, organization,
city, postalcode, addresspart, country, auid, indexed_name,
surname, given_name).
If "given_name" is not present, fall back to initials.
Note: Affiliation information might be missing or mal-assigned even
when it lookes correct in the web view. In this case please request
a correction.
"""
out = []
fields = 'affiliation_id dptid organization city postalcode '\
'addresspart country auid indexed_name surname given_name'
auth = namedtuple('Author', fields)
items = listify(self._head.get('author-group', []))
for item in items:
# Affiliation information
aff = item.get('affiliation', {})
try:
aff_ids = listify(aff['affiliation-id'])
aff_id = ", ".join([a["@afid"] for a in aff_ids])
except KeyError:
aff_id = aff.get("@afid")
org = _get_org(aff)
# Author information (might relate to collaborations)
authors = listify(item.get('author', item.get('collaboration', [])))
for au in authors:
try:
given = au.get('ce:given-name', au['ce:initials'])
except KeyError: # Collaboration
given = au.get('ce:text')
new = auth(affiliation_id=aff_id, organization=org,
city=aff.get('city'), dptid=aff.get("@dptid"),
postalcode=aff.get('postal-code'),
addresspart=aff.get('address-part'),
country=aff.get('country'), auid=au.get('@auid'),
surname=au.get('ce:surname'), given_name=given,
indexed_name=chained_get(au, ['preferred-name', 'ce:indexed-name']))
out.append(new)
return out or None
def authorgroup(self):
"""A list of namedtuples representing the article's authors organized
by affiliation, in the form (affiliation_id, organization, city_group,
country, auid, indexed_name, surname, given_name). If "given_name"
is not present, fall back to initials.
Note: Affiliation information might be missing or mal-assigned even
when it lookes correct in the web view. In this case please request
a correction.
"""
out = []
fields = 'affiliation_id organization city_group country '\
'auid indexed_name surname given_name'
auth = namedtuple('Author', fields)
items = listify(self._head.get('author-group', []))
for item in items:
# Affiliation information
aff = item.get('affiliation', {})
aff_ids = listify(aff['affiliation-id'])
aff_id = ", ".join([a["@afid"] for a in aff_ids])
org = _get_org(aff)
# Author information (might relate to collaborations)
authors = listify(item.get('author', item.get('collaboration',
[])))
for au in authors:
try:
given = au.get('ce:given-name', au['ce:initials'])
except KeyError: # Collaboration
given = au.get('ce:text')
new = auth(affiliation_id=aff_id,
organization=org,
city_group=aff.get('city-group'),
country=aff.get('country'),
auid=au.get('@auid'),
surname=au.get('ce:surname'),
given_name=given,
indexed_name=chained_get(
au, ['preferred-name', 'ce:indexed-name']))
out.append(new)
return out or None
def chemicals(self):
"""List of namedtuples representing chemical entities in the form
(source, chemical_name, cas_registry_number). In case multiple
numbers given, they are joined on ";".
"""
path = ['enhancement', 'chemicalgroup', 'chemicals']
items = listify(chained_get(self._head, path, []))
chemical = namedtuple('Chemical',
'source chemical_name cas_registry_number')
out = []
for item in items:
for chem in listify(item['chemical']):
number = chem.get('cas-registry-number')
try: # Multiple numbers given
num = ";".join([n['$'] for n in number])
except TypeError:
num = number
new = chemical(source=item['@source'],
cas_registry_number=num,
chemical_name=chem['chemical-name'])
out.append(new)
return out or None
def subject_areas(self):
"""List of namedtuples containing subject areas of the article
in the form ().
Note: Requires the FULL view of the article.
"""
area = namedtuple('Area', 'area abbreviation code')
path = ['subject-areas', 'subject-area']
out = [
area(area=item['$'],
abbreviation=item['@abbrev'],
code=item['@code'])
for item in listify(chained_get(self._json, path, []))
]
return out or None
def affiliation(self):
"""A list of namedtuples representing listed affiliations in
the form (id, name, city, country).
Note: Might be empty.
"""
out = []
aff = namedtuple('Affiliation', 'id name city country')
affs = listify(self._json.get('affiliation', []))
for item in affs:
new = aff(id=item.get('@id'), name=item.get('affilname'),
city=item.get('affiliation-city'),
country=item.get('affiliation-country'))
out.append(new)
return out or None
def journal_history(self):
"""List of named tuples of authored publications in the form
(sourcetitle, abbreviation, type, issn). issn is only given
for journals. abbreviation and issn may be None.
"""
jour = namedtuple('Journal', 'sourcetitle abbreviation type issn')
path = ['author-profile', 'journal-history', 'journal']
hist = [
jour(sourcetitle=pub['sourcetitle'],
issn=pub.get('issn'),
abbreviation=pub.get('sourcetitle-abbrev'),
type=pub['@type'])
for pub in listify(chained_get(self._json, path, []))
]
return hist or None
def affiliation(self):
"""A list of namedtuples representing listed affiliations in
the form (id, name, city, country).
Note: Might be empty.
"""
out = []
aff = namedtuple('Affiliation', 'id name city country')
affs = listify(self._json.get('affiliation', []))
for item in affs:
new = aff(id=item.get('@id'),
name=item.get('affilname'),
city=item.get('affiliation-city'),
country=item.get('affiliation-country'))
out.append(new)
return out or None
def contributor_group(self):
"""List of namedtuples representing contributors compiled by Scopus,
in the form (given_name, initials, surname, indexed_name, role).
"""
items = listify(chained_get(self._head, ['source', 'contributor-group'], []))
out = []
fields = 'given_name initials surname indexed_name role'
pers = namedtuple('Contributor', fields)
for item in items:
entry = item.get('contributor', {})
new = pers(indexed_name=entry.get('ce:indexed-name'),
role=entry.get('@role'), surname=entry.get('ce:surname'),
given_name=entry.get('ce:given-name'),
initials=entry.get('ce:initials'))
out.append(new)
return out or None
def funding(self):
"""List of namedtuples parsed funding information in the form
(agency string id acronym country).
"""
path = ['item', 'xocs:meta', 'xocs:funding-list', 'xocs:funding']
funds = listify(chained_get(self._json, path, []))
out = []
fund = namedtuple('Funding', 'agency string id acronym country')
for item in funds:
new = fund(agency=item.get('xocs:funding-agency'),
string=item.get('xocs:funding-agency-matched-string'),
id=item.get('xocs:funding-agency-id'),
acronym=item.get('xocs:funding-agency-acronym'),
country=item.get('xocs:funding-agency-country'))
out.append(new)
return out or None
def funding(self):
"""List of namedtuples parsed funding information in the form
(agency string id acronym country).
"""
path = ['item', 'xocs:meta', 'xocs:funding-list', 'xocs:funding']
funds = listify(chained_get(self._json, path, []))
out = []
fund = namedtuple('Funding', 'agency string id acronym country')
for item in funds:
new = fund(agency=item.get('xocs:funding-agency'),
string=item.get('xocs:funding-agency-matched-string'),
id=item.get('xocs:funding-agency-id'),
acronym=item.get('xocs:funding-agency-acronym'),
country=item.get('xocs:funding-agency-country'))
out.append(new)
return out or None
def name_variants(self):
"""List of named tuples containing variants of the author name with
number of documents published with that variant.
"""
fields = 'indexed_name initials surname given_name doc_count'
variant = namedtuple('Variant', fields)
path = ['author-profile', 'name-variant']
out = [
variant(indexed_name=var['indexed-name'],
surname=var['surname'],
doc_count=var.get('@doc-count'),
initials=var['initials'],
given_name=var.get('given-name'))
for var in listify(chained_get(self._json, path, []))
]
return out or None
def contributor_group(self):
"""List of namedtuples representing contributors compiled by Scopus,
in the form (given_name, initials, surname, indexed_name, role).
"""
items = listify(
chained_get(self._head, ['source', 'contributor-group'], []))
out = []
fields = 'given_name initials surname indexed_name role'
pers = namedtuple('Contributor', fields)
for item in items:
entry = item.get('contributor', {})
new = pers(indexed_name=entry.get('ce:indexed-name'),
role=entry.get('@role'),
surname=entry.get('ce:surname'),
given_name=entry.get('ce:given-name'),
initials=entry.get('ce:initials'))
out.append(new)
return out or None
def authors(self):
"""A list of namedtuples representing the article's authors, in the
form (auid, indexed_name, surname, given_name, affiliation_id,
affiliation, city, country).
Note: The affiliation referred to here is what Scopus' algorithm
determined as the main affiliation. Property `authorgroup` provides
all affiliations.
"""
out = []
fields = 'auid indexed_name surname given_name affiliation'
auth = namedtuple('Author', fields)
for item in chained_get(self._json, ['authors', 'author'], []):
affs = [a for a in listify(item.get('affiliation')) if a]
if affs:
aff = [aff.get('@id') for aff in affs]
else:
aff = None
new = auth(auid=item['@auid'], surname=item.get('ce:surname'),
indexed_name=item.get('ce:indexed-name'), affiliation=aff,
given_name=chained_get(item, ['preferred-name', 'ce:given-name']))
out.append(new)
return out or None
def references(self):
"""List of namedtuples representing references listed in the abstract,
in the form (position, id, doi, title, authors, authors_auid,
authors_affiliationid, sourcetitle, publicationyear, volume, issue, first,
last, citedbycount, text, fulltext).
`position` is the number at which the reference appears in the
document, `id` is the Scopus ID of the referenced abstract (EID
without the "2-s2.0-"), `authors` is a string of the names of the
authors in the format "Surname1, Initials1; Surname2, Initials2",
`authors_auid` is a string of the author IDs joined on "; ",
`authors_affiliationid` is a string of the authors' affiliation IDs
joined on "; ", `sourcetitle` is the name of the source (e.g. the
journal), `publicationyear` is the year of the publication as a string,
`volume` and `issue`, are strings referring to the volume and issue,
`first` and `last` refer to the page range, `citedbycount` is a string
for the total number of citations of the cited item, `text` is
Scopus-provided information on the publication, `fulltext` is the text
the authors used for the reference.
Note: Requires either the FULL view or REF view of the article. Might
be empty even if refcount is positive. Specific fields can be empty.
Author lists (authors, authors_auid, authors_affiliationid) may contain
duplicates but have been filtered of None's.
"""
out = []
fields = 'position id doi title authors authors_auid '\
'authors_affiliationid sourcetitle publicationyear volume '\
'issue first last citedbycount text fulltext'
ref = namedtuple('Reference', fields)
path = ['item', 'bibrecord', 'tail', 'bibliography', 'reference']
items = listify(chained_get(self._json, path,
self._json.get('references', {}).get('reference', [])))
for item in items:
info = item.get('ref-info', item)
volisspag = info.get('volisspag', {}) or {}
if isinstance(volisspag, list):
volisspag = volisspag[0]
# Parse author information
try: # FULL view parsing
auth = listify(item['ref-info']['ref-authors']['author'])
authors = [', '.join([d['ce:surname'], d['ce:initials']])
for d in auth]
auids = None
affids = None
except KeyError: # REF view parsing
auth = (info.get('author-list') or {}).get('author', [])
authors = [', '.join(filter(None, [d.get('ce:surname'),
d.get('ce:given-name')]))
for d in auth]
auids = "; ".join(filter(None, [d.get('@auid') for d in auth]))
affs = filter(None, [d.get('affiliation') for d in auth])
affids = "; ".join([aff.get('@id') for aff in affs])
# Parse IDs
try:
ids = listify(info['refd-itemidlist']['itemid'])
except KeyError:
ids = []
try:
doi = _select_by_idtype(ids, 'DOI')[0]
except IndexError:
doi = info.get('ce:doi')
try:
scopus_id = _select_by_idtype(ids, 'SGR')[0]
except IndexError:
scopus_id = info.get('scopus-id')
# Combine information
new = ref(position=item.get('@id'),
id=scopus_id,
doi=doi,
authors="; ".join(authors),
authors_auid=auids or None,
authors_affiliationid=affids or None,
title=info.get('ref-title', {}).get('ref-titletext', info.get('title')),
sourcetitle=info.get('ref-sourcetitle', info.get('sourcetitle')),
publicationyear=info.get('ref-publicationyear', {}).get('@first'),
volume=volisspag.get('voliss', {}).get('@volume'),
issue=volisspag.get('voliss', {}).get('@issue'),
first=volisspag.get('pagerange', {}).get('@first'),
last=volisspag.get('pagerange', {}).get('@last'),
citedbycount=info.get('citedby-count'),
text=info.get('ref-text'),
fulltext=item.get('ref-fulltext'))
out.append(new)
return out or None
def results(self):
"""A list of namedtuples in the form (eid doi pii pubmed_id title
subtype creator afid affilname affiliation_city affiliation_country
author_count author_names author_ids author_afids coverDate
coverDisplayDate publicationName issn source_id eIssn aggregationType
volume issueIdentifier article_number pageRange description
authkeywords citedby_count openaccess fund_acr fund_no fund_sponsor).
Field definitions correspond to
https://dev.elsevier.com/guides/ScopusSearchViews.htm, except for
afid, affilname, affiliation_city, affiliation_country, author_count,
author_names, author_ids and author_afids: These information are
joined on ";". In case an author has multiple affiliations, they are
joined on "-" (e.g. Author1Aff;Author2Aff1-Author2Aff2).
Notes
-----
The list of authors and the list of affiliations per author are
deduplicated.
"""
out = []
fields = 'eid doi pii pubmed_id title subtype creator afid affilname '\
'affiliation_city affiliation_country author_count '\
'author_names author_ids author_afids coverDate '\
'coverDisplayDate publicationName issn source_id eIssn '\
'aggregationType volume issueIdentifier article_number '\
'pageRange description authkeywords citedby_count '\
'openaccess fund_acr fund_no fund_sponsor'
doc = namedtuple('Document', fields)
for item in self._json:
info = {}
# Parse affiliations
try:
info["affilname"] = _join(item['affiliation'], 'affilname')
info["afid"] = _join(item['affiliation'], 'afid')
info["aff_city"] = _join(item['affiliation'],
'affiliation-city')
info["aff_country"] = _join(item['affiliation'],
'affiliation-country')
except KeyError:
pass
# Parse authors
try:
# Deduplicate list of authors
authors = _deduplicate(item['author'])
# Extract information
surnames = _replace_none([d['surname'] for d in authors])
firstnames = _replace_none([d['given-name'] for d in authors])
info["auth_names"] = ";".join([
", ".join([t[0], t[1]]) for t in zip(surnames, firstnames)
])
info["auth_ids"] = ";".join([d['authid'] for d in authors])
affs = []
for auth in authors:
aff = listify(_deduplicate(auth.get('afid', [])))
affs.append('-'.join([d['$'] for d in aff]))
info["auth_afid"] = (';'.join(affs) or None)
except KeyError:
pass
date = item.get('prism:coverDate')
if isinstance(date, list):
date = date[0].get('$')
new = doc(article_number=item.get('article-number'),
title=item.get('dc:title'),
fund_sponsor=item.get('fund-sponsor'),
subtype=item.get('subtype'),
issn=item.get('prism:issn'),
creator=item.get('dc:creator'),
affilname=info.get("affilname"),
author_names=info.get("auth_names"),
doi=item.get('prism:doi'),
coverDate=date,
volume=item.get('prism:volume'),
coverDisplayDate=item.get('prism:coverDisplayDate'),
publicationName=item.get('prism:publicationName'),
source_id=item.get('source-id'),
author_ids=info.get("auth_ids"),
aggregationType=item.get('prism:aggregationType'),
issueIdentifier=item.get('prism:issueIdentifier'),
pageRange=item.get('prism:pageRange'),
author_afids=info.get("auth_afid"),
fund_no=item.get('fund-no'),
affiliation_country=info.get("aff_country"),
citedby_count=item.get('citedby-count'),
openaccess=item.get('openaccess'),
eIssn=item.get('prism:eIssn'),
author_count=item.get('author-count', {}).get('$'),
affiliation_city=info.get("aff_city"),
afid=info.get("afid"),
description=item.get('dc:description'),
pii=item.get('pii'),
authkeywords=item.get('authkeywords'),
eid=item['eid'],
fund_acr=item.get('fund-acr'),
pubmed_id=item.get('pubmed-id'))
out.append(new)
return out or None
def results(self):
"""A list of namedtuples in the form (eid doi pii pubmed_id title
subtype creator afid affilname affiliation_city affiliation_country
author_count author_names author_ids author_afids coverDate
coverDisplayDate publicationName issn source_id eIssn aggregationType
volume issueIdentifier article_number pageRange description
authkeywords citedby_count openaccess fund_acr fund_no fund_sponsor).
Field definitions correspond to
https://dev.elsevier.com/guides/ScopusSearchViews.htm, except for
afid, affilname, affiliation_city, affiliation_country, author_count,
author_names, author_ids and author_afids: These information are
joined on ";". In case an author has multiple affiliations, they are
joined on "-" (e.g. Author1Aff;Author2Aff1-Author2Aff2).
Notes
-----
The list of authors and the list of affiliations per author are
deduplicated.
"""
out = []
fields = 'eid doi pii pubmed_id title subtype creator afid affilname '\
'affiliation_city affiliation_country author_count '\
'author_names author_ids author_afids coverDate '\
'coverDisplayDate publicationName issn source_id eIssn '\
'aggregationType volume issueIdentifier article_number '\
'pageRange description authkeywords citedby_count '\
'openaccess fund_acr fund_no fund_sponsor'
doc = namedtuple('Document', fields)
for item in self._json:
info = {}
# Parse affiliations
try:
info["affilname"] = _join(item['affiliation'], 'affilname')
info["afid"] = _join(item['affiliation'], 'afid')
info["aff_city"] = _join(item['affiliation'], 'affiliation-city')
info["aff_country"] = _join(item['affiliation'],
'affiliation-country')
except KeyError:
pass
# Parse authors
try:
# Deduplicate list of authors
authors = _deduplicate(item['author'])
# Extract information
surnames = _replace_none([d['surname'] for d in authors])
firstnames = _replace_none([d['given-name'] for d in authors])
info["auth_names"] = ";".join([", ".join([t[0], t[1]]) for t in
zip(surnames, firstnames)])
info["auth_ids"] = ";".join([d['authid'] for d in authors])
affs = []
for auth in authors:
aff = listify(_deduplicate(auth.get('afid', [])))
affs.append('-'.join([d['$'] for d in aff]))
info["auth_afid"] = (';'.join(affs) or None)
except KeyError:
pass
date = item.get('prism:coverDate')
if isinstance(date, list):
date = date[0].get('$')
new = doc(article_number=item.get('article-number'),
title=item.get('dc:title'), fund_sponsor=item.get('fund-sponsor'),
subtype=item.get('subtype'), issn=item.get('prism:issn'),
creator=item.get('dc:creator'), affilname=info.get("affilname"),
author_names=info.get("auth_names"), doi=item.get('prism:doi'),
coverDate=date, volume=item.get('prism:volume'),
coverDisplayDate=item.get('prism:coverDisplayDate'),
publicationName=item.get('prism:publicationName'),
source_id=item.get('source-id'), author_ids=info.get("auth_ids"),
aggregationType=item.get('prism:aggregationType'),
issueIdentifier=item.get('prism:issueIdentifier'),
pageRange=item.get('prism:pageRange'),
author_afids=info.get("auth_afid"), fund_no=item.get('fund-no'),
affiliation_country=info.get("aff_country"),
citedby_count=item.get('citedby-count'),
openaccess=item.get('openaccess'), eIssn=item.get('prism:eIssn'),
author_count=item.get('author-count', {}).get('$'),
affiliation_city=info.get("aff_city"), afid=info.get("afid"),
description=item.get('dc:description'), pii=item.get('pii'),
authkeywords=item.get('authkeywords'), eid=item['eid'],
fund_acr=item.get('fund-acr'), pubmed_id=item.get('pubmed-id'))
out.append(new)
return out or None
def references(self):
"""List of namedtuples representing references listed in the abstract,
in the form (position, id, doi, title, authors, authors_auid,
authors_affiliationid, sourcetitle, publicationyear, volume, issue, first,
last, citedbycount, text, fulltext).
`position` is the number at which the reference appears in the
document, `id` is the Scopus ID of the referenced abstract (EID
without the "2-s2.0-"), `authors` is a string of the names of the
authors in the format "Surname1, Initials1; Surname2, Initials2",
`authors_auid` is a string of the author IDs joined on "; ",
`authors_affiliationid` is a string of the authors' affiliation IDs
joined on "; ", `sourcetitle` is the name of the source (e.g. the
journal), `publicationyear` is the year of the publication as a string,
`volume` and `issue`, are strings referring to the volume and issue,
`first` and `last` refer to the page range, `citedbycount` is a string
for the total number of citations of the cited item, `text` is
Scopus-provided information on the publication, `fulltext` is the text
the authors used for the reference.
Note: Requires either the FULL view or REF view of the article. Might
be empty even if refcount is positive. Specific fields can be empty.
Author lists (authors, authors_auid, authors_affiliationid) may contain
duplicates but have been filtered of None's.
"""
out = []
fields = 'position id doi title authors authors_auid '\
'authors_affiliationid sourcetitle publicationyear volume '\
'issue first last citedbycount text fulltext'
ref = namedtuple('Reference', fields)
path = ['item', 'bibrecord', 'tail', 'bibliography', 'reference']
items = listify(
chained_get(self._json, path,
self._json.get('references', {}).get('reference', [])))
for item in items:
info = item.get('ref-info', item)
volisspag = info.get('volisspag', {}) or {}
if isinstance(volisspag, list):
volisspag = volisspag[0]
# Parse author information
try: # FULL view parsing
auth = listify(item['ref-info']['ref-authors']['author'])
authors = [
', '.join([d['ce:surname'], d['ce:initials']])
for d in auth
]
auids = None
affids = None
except KeyError: # REF view parsing
auth = (info.get('author-list') or {}).get('author', [])
authors = [
', '.join(
filter(None,
[d.get('ce:surname'),
d.get('ce:given-name')])) for d in auth
]
auids = "; ".join(filter(None, [d.get('@auid') for d in auth]))
affs = filter(None, [d.get('affiliation') for d in auth])
affids = "; ".join([aff.get('@id') for aff in affs])
# Parse IDs
try:
ids = listify(info['refd-itemidlist']['itemid'])
except KeyError:
ids = []
try:
doi = [d['$'] for d in ids if d['@idtype'] == 'DOI'][0]
except IndexError:
doi = info.get('ce:doi')
try:
scopus_id = [d['$'] for d in ids if d['@idtype'] == 'SGR'][0]
except IndexError:
scopus_id = info.get('scopus-id')
# Combine information
new = ref(position=item.get('@id'),
id=scopus_id,
doi=doi,
authors="; ".join(authors),
authors_auid=auids or None,
authors_affiliationid=affids or None,
title=info.get('ref-title',
{}).get('ref-titletext',
info.get('title')),
sourcetitle=info.get('ref-sourcetitle',
info.get('sourcetitle')),
publicationyear=info.get('ref-publicationyear',
{}).get('@first'),
volume=volisspag.get('voliss', {}).get('@volume'),
issue=volisspag.get('voliss', {}).get('@issue'),
first=volisspag.get('pagerange', {}).get('@first'),
last=volisspag.get('pagerange', {}).get('@last'),
citedbycount=info.get('citedby-count'),
text=info.get('ref-text'),
fulltext=item.get('ref-fulltext'))
out.append(new)
return out or None
