def retrieve_author(self, author_id, show=True, verbose=False):
#{{{ retrieve author info
import warnings
import numpy as np
import pandas as pd
from urllib import quote
from urllib2 import urlopen
from utils import _parse_author_retrieval
from bs4 import BeautifulSoup as bs
#TODO: Verbose mode;
'''
Search for specific authors
Details: http://api.elsevier.com/documentation/AuthorRetrievalAPI.wadl
returns a dictionary
'''
# parse query dictionary
url = self._author_retrieve_url_base +\
'{}?apikey={}&httpAccept=application/xml'.format(author_id, self.apikey)
soup = bs(urlopen(url).read(), 'lxml')
with open('test.xml', 'wb') as testxml:
testxml.write(soup.prettify())
author_info = _parse_author_retrieval(soup)
# nothing find
if not author_info:
print 'No matched record found!'
return None
if show:
print 'Name: %s' %(author_info['first-name'] + ' ' + author_info['last-name'])
print 'Affiliation: %s (%s)' %(author_info['current-affiliation'][0]['name'],\
author_info['current-affiliation'][0]['address'])
# }}}
return author_info
def retrieve_author(self, author_id, show=True, verbose=False, save_xml='./author_xmls'):
#{{{ retrieve author info
'''
Search for specific authors
Details: http://api.elsevier.com/documentation/AuthorRetrievalAPI.wadl
returns a dictionary
'''
# parse query dictionary
url = self._author_retrieve_url_base +\
'{}?apikey={}&httpAccept=application/xml'.format(author_id, self.apikey)
soup = bs(urlopen(url).read(), 'lxml')
if save_xml is not None:
if not os.path.exists(save_xml):
os.makedirs(save_xml)
with io.open('%s/%s.xml' %(save_xml, author_id), 'w', encoding='utf-8') as author_xml:
author_xml.write(soup.prettify())
author_info = _parse_author_retrieval(soup)
# nothing find
if not author_info:
print 'No matched record found!'
return None
if show:
print 'Name: %s' %(author_info['first-name'] + ' ' + author_info['last-name'])
print 'Affiliation: %s (%s)' %(author_info['current-affiliation'][0]['name'],\
author_info['current-affiliation'][0]['address'])
# }}}
return author_info
def retrieve_author(self, author_id):
'''
Search for specific authors
Details: http://api.elsevier.com/documentation/AuthorRetrievalAPI.wadl
Parameters
----------------------------------------------------------------------
author_id : str
Author id in Scopus database.
Returns
----------------------------------------------------------------------
dict
Dictionary of author information.
'''
par = {'apikey': self.apikey, 'httpAccept': 'application/json'}
r = requests.get('%s/%s' % (APIURI.AUTHOR, author_id), params=par)
js = r.json()
try:
return _parse_author_retrieval(js)
except:
raise ValueError('Author %s not found!' % author_id)