How to use pybliometrics - 10 common examples

Notes
        -----
        The files are cached in ~/.scopus/author_retrieval/ENHANCED/{author_id}
        (without eventually leading '9-s2.0-').
        """
        # Load json
        view = "ENHANCED"  # In case Scopus adds different views in future
        self._id = str(int(str(author_id).split('-')[-1]))
        Retrieval.__init__(self, identifier=self._id, api='AuthorRetrieval',
                           refresh=refresh, view=view)
        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)

aff_id : str or int
            The Scopus Affiliation ID.  Optionally expressed
            as an Elsevier EID (i.e., in the form 10-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/affiliation_retrieval/STANDARD/{aff_id}.
        """
        view = "STANDARD"  # In case Scopus adds different views in future

        # Load json
        aff_id = str(int(str(aff_id).split('-')[-1]))
        Retrieval.__init__(self, identifier=aff_id, view=view, refresh=refresh,
                           api='ContentAffiliationRetrieval')

        self._json = self._json['affiliation-retrieval-response']

from collections import namedtuple
from datetime import datetime

from pybliometrics.scopus.classes import Retrieval


class CitationOverview(Retrieval):
    @property
    def authors(self):
        """A list of namedtuples storing author information,
        where each namedtuple corresponds to one author.
        The information in each namedtuple is (name surname initials id url).
        All entries are strings.
        """
        out = []
        order = 'name surname initials id url'
        auth = namedtuple('Author', order)
        for author in self._citeInfoMatrix.get('author'):
            author = {k.split(":", 1)[-1]: v for k, v in author.items()}
            new = auth(name=author.get('index-name'), id=author.get('authid'),
                       surname=author.get('surname'),
                       initials=author.get('initials'),
                       url=author.get('author-url'))

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/ENHANCED/{author_id}
        (without eventually leading '9-s2.0-').
        """
        # Load json
        view = "ENHANCED"  # In case Scopus adds different views in future
        self._id = str(int(str(author_id).split('-')[-1]))
        Retrieval.__init__(self, identifier=self._id, api='AuthorRetrieval',
                           refresh=refresh, view=view)
        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)

Note: These information will not be cached and are slow for large
        coauthor groups.
        """
        # Get number of authors to search for
        res = cache_file(url=self.coauthor_link)
        data = loads(res.text)['search-results']
        N = int(data.get('opensearch:totalResults', 0))
        # Store information in namedtuples
        fields = 'surname given_name id areas affiliation_id name city country'
        coauth = namedtuple('Coauthor', fields)
        coauthors = []
        # Iterate over search results in chunks of 25 results
        count = 0
        while count < N:
            params = {'start': count, 'count': 25}
            res = cache_file(url=self.coauthor_link, params=params, accept='json')
            data = loads(res.text)['search-results'].get('entry', [])
            # Extract information for each coauthor
            for entry in data:
                aff = entry.get('affiliation-current', {})
                try:
                    areas = [a['$'] for a in entry.get('subject-area', [])]
                except TypeError:  # Only one subject area given
                    areas = [entry['subject-area']['$']]
                new = coauth(surname=entry['preferred-name']['surname'],
                    given_name=entry['preferred-name'].get('given-name'),
                    id=entry['dc:identifier'].split(':')[-1],
                    areas='; '.join(areas), name=aff.get('affiliation-name'),
                    affiliation_id=aff.get('affiliation-id'),
                    city=aff.get('affiliation-city'),
                    country=aff.get('affiliation-country'))
                coauthors.append(new)

def source_id(self):
        """Scopus source ID of the document."""
        return chained_get(self._json, ['coredata', 'source-id'])

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.get('sourcetitle'), issn=pub.get('issn'),
                     abbreviation=pub.get('sourcetitle-abbrev'),
                     type=pub.get('@type'))
                for pub in listify(chained_get(self._json, path, []))]
        return hist or None

def given_name(self):
        """Author's preferred given name."""
        path = ['author-profile', 'preferred-name', 'given-name']
        return chained_get(self._json, path)

def status(self):
        """The status of the author profile."""
        return chained_get(self._json, ["author-profile", "status"])

def publicationName(self):
        """Name of source the document is published in."""
        return chained_get(self._json, ['coredata', 'prism:publicationName'])