def orcid_author_search_parser(author_name):
"""
Method to parse the list of matching authors from ORCID website into an array object, given the name of the author
"""
out_file = "data/orcid_author_search.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_search(author_name,
kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
authors = []
for child1 in root_element:
if (child1.tag == ns + 'orcid-search-results'):
for child2 in child1:
if (child2.tag == ns + 'orcid-search-result'):
author = {'othernames': []}
for child3 in child2:
if (child3.tag == ns + 'orcid-profile'):
for child4 in child3:
if (child4.tag == ns + 'orcid-identifier'):
for child5 in child4:
if (child5.tag == ns + 'path'):
author['orcid'] = child5.text
elif (child4.tag == ns + 'orcid-bio'):
for child5 in child4:
if (child5.tag == ns +
'personal-details'):
for child6 in child5:
if (child6.tag == ns +
'given-names'):
author[
'firstname'] = child6.text
elif (child6.tag == ns +
'family-name'):
author[
'lastname'] = child6.text
elif (child6.tag == ns +
'other-names'):
for child7 in child6:
if (child7.tag ==
ns +
'other-name'
):
author[
'othernames'].append(
child7.
text)
author = ORCID_Parser.generate_author_other_names(
author)
authors.append(author)
return authors
def orcid_author_search_parser(author_name):
"""
Method to parse the list of matching authors from ORCID website into an array object, given the name of the author
"""
out_file = "data/orcid_author_search.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_search(author_name, kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
authors = []
for child1 in root_element:
if(child1.tag == ns + 'orcid-search-results'):
for child2 in child1:
if(child2.tag == ns + 'orcid-search-result'):
author = {'othernames': []}
for child3 in child2:
if(child3.tag == ns + 'orcid-profile'):
for child4 in child3:
if(child4.tag == ns + 'orcid-identifier'):
for child5 in child4:
if(child5.tag == ns + 'path'):
author['orcid'] = child5.text
elif(child4.tag == ns + 'orcid-bio'):
for child5 in child4:
if(child5.tag == ns + 'personal-details'):
for child6 in child5:
if(child6.tag == ns + 'given-names'):
author['firstname'] = child6.text
elif(child6.tag == ns + 'family-name'):
author['lastname'] = child6.text
elif(child6.tag == ns + 'other-names'):
for child7 in child6:
if(child7.tag == ns + 'other-name'):
author['othernames'].append(child7.text)
author = ORCID_Parser.generate_author_other_names(author)
authors.append(author)
return authors
from lookup.ORCID import ORCID
import json
fout = open("orcid_author_details.txt", "w")
def banner(msg):
print >> fout, 70 * "="
print >> fout, msg
print >> fout, 70 * "="
banner("orcid author details xml")
print >> fout, ORCID.orcid_author_get("0000-0001-9558-179X", kind="xml").encode('utf-8')
banner("orcid author details json")
print >> fout, json.dumps(ORCID.orcid_author_get("0000-0001-9558-179X", kind="json"), indent=2).encode('utf-8')
banner("orcid author works xml")
print >> fout, ORCID.orcid_author_works_get("0000-0001-9558-179X", kind="xml").encode('utf-8')
banner("orcid author works json")
print >> fout, json.dumps(ORCID.orcid_author_works_get("0000-0001-9558-179X", kind="json"), indent=2).encode('utf-8')
from lookup.ORCID import ORCID
import json
fout = open("orcid_author_details_by_name.txt", "w")
def banner(msg):
print >> fout, 70 * "="
print >> fout, msg
print >> fout, 70 * "="
banner("orcid author details xml")
print >> fout, ORCID.orcid_author_search("gregor von laszewski", kind="xml").encode('utf-8')
banner("orcid author details json")
print >> fout, json.dumps(ORCID.orcid_author_search("gregor von laszewski", kind="json"), indent=2).encode('utf-8')
def orcid_author_get_parser(orcid):
"""
Method to parse the author details from ORCID website into a dictionary object, given the orcid of the author
"""
out_file = "data/orcid_author_get.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_get(orcid,
kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
author = {'othernames': [], 'urls': [], 'identifiers': []}
for child1 in root_element:
if (child1.tag == ns + 'orcid-profile'):
for child2 in child1:
if (child2.tag == ns + 'orcid-identifier'):
for child3 in child2:
if (child3.tag == ns + 'path'):
author['orcid'] = child3.text
elif (child2.tag == ns + 'orcid-bio'):
for child3 in child2:
if (child3.tag == ns + 'personal-details'):
for child4 in child3:
if (child4.tag == ns + 'given-names'):
author['firstname'] = child4.text
elif (child4.tag == ns + 'family-name'):
author['lastname'] = child4.text
elif (child4.tag == ns + 'other-names'):
for child5 in child4:
if (child5.tag == ns +
'other-name'):
author['othernames'].append(
child5.text)
elif (child3.tag == ns + 'researcher-urls'):
for child4 in child3:
if (child4.tag == ns + 'researcher-url'):
for child5 in child4:
if (child5.tag == ns + 'url'):
author['urls'].append(
child5.text)
elif (child3.tag == ns + 'contact-details'):
for child4 in child3:
if (child4.tag == ns + 'email'):
author['email'] = child4.text
elif (child3.tag == ns + 'external-identifiers'):
for child4 in child3:
if (child4.tag == ns +
'external-identifier'):
identifier = {}
for child5 in child4:
if (child5.tag == ns +
'external-id-common-name'):
key = None
if (child5.text ==
'ResearcherID'):
key = 'ResearcherID'
elif (child5.text ==
'Scopus Author ID'):
key = 'ScopusID'
elif (child5.tag == ns +
'external-id-reference'):
value = child5.text
if key is not None:
identifier[key] = value
author['identifiers'].append(
identifier)
return author
def orcid_author_works_get_parser(orcid):
"""
Method to parse the author works from ORCID website into a dictionary object, given the orcid of the author
"""
out_file = "data/orcid_author_works_get.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_works_get(orcid,
kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
author = {'works': []}
for child1 in root_element:
if (child1.tag == ns + 'orcid-profile'):
for child2 in child1:
if (child2.tag == ns + 'orcid-identifier'):
for child3 in child2:
if (child3.tag == ns + 'path'):
author['orcid'] = child3.text
elif (child2.tag == ns + 'orcid-activities'):
for child3 in child2:
if (child3.tag == ns + 'orcid-works'):
for child4 in child3:
if (child4.tag == ns + 'orcid-work'):
work = {
'identifiers': [],
'authorIDs': []
}
for child5 in child4:
if (child5.tag == ns +
'work-title'):
for child6 in child5:
if (child6.tag == ns +
'title'):
work[
'title'] = child6.text
elif (child5.tag == ns +
'journal-title'):
work[
'journalTitle'] = child5.text
elif (child5.tag == ns +
'work-citation'):
for child6 in child5:
if (child6.tag == ns +
'work-citation-type'
):
work[
'work-citation-type'] = child6.text
elif (child6.tag == ns +
'citation'):
citation = child6.text
if (work['work-citation-type']
== 'bibtex'):
work[
'authors'] = ORCID_Parser.get_authors_list_from_bibtex(
citation)
elif (work[
'work-citation-type']
==
'formatted-unspecified'):
work[
'authors'] = ORCID_Parser.get_authors_list_from_unformattedtext(
citation)
elif (child5.tag == ns +
'publication-date'):
for child6 in child5:
if (child6.tag == ns +
'year'):
work[
'year'] = child6.text
elif (child5.tag == ns +
'work-external-identifiers'):
for child6 in child5:
if (child6.tag == ns +
'work-external-identifier'
):
identifier = {}
for child7 in child6:
if (child7.tag ==
ns +
'work-external-identifier-type'
):
key = None
if (child7.text
==
'doi'):
key = 'doi'
elif (child7.tag ==
ns +
'work-external-identifier-id'
):
value = child7.text
if key is not None:
identifier[
key] = value
work[key] = value
work[
'identifiers'].append(
identifier)
if 'title' not in work:
work['title'] = ''
if 'doi' not in work:
publications = IEEE_Parser.ieee_publication_search_parser(
work['title'])
if (len(publications) == 1):
for publication in publications:
work['doi'] = publication[
'doi']
else:
work['doi'] = ''
if 'authors' not in work:
work['authors'] = []
author['works'].append(work)
return author
def banner(msg):
print 70 * "="
print msg
print 70 * "="
banner("doi turtle")
print DOI.doi_get("10.1109/GCE.2010.5676126", kind="turle")
banner("doi bibtex")
print DOI.doi_get("10.1109/GCE.2010.5676126")
banner("doi json")
pprint(DOI.doi_get("10.1109/GCE.2010.5676126", kind="json"))
banner("ieee xml")
print IEEE.ieee_doi_get("10.1109/GCE.2010.5676126", kind="xml")
banner("ieee json")
print IEEE.ieee_doi_get("10.1109/GCE.2010.5676126", kind="json")
banner("orcid xml")
print ORCID.orcid_doi_get("10.1109/GCE.2010.5676126", kind="xml")
banner("orcid json")
print json.dumps(ORCID.orcid_doi_get("10.1109/GCE.2010.5676126", kind="json"), indent=2)
banner("crossref json")
pprint(CrossRef.crossref_doi_get("10.1109/GCE.2010.5676126", kind="json"))
def orcid_author_get_parser(orcid):
"""
Method to parse the author details from ORCID website into a dictionary object, given the orcid of the author
"""
out_file = "data/orcid_author_get.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_get(orcid, kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
author = {'othernames': [], 'urls': [], 'identifiers': []}
for child1 in root_element:
if(child1.tag == ns + 'orcid-profile'):
for child2 in child1:
if(child2.tag == ns + 'orcid-identifier'):
for child3 in child2:
if(child3.tag == ns + 'path'):
author['orcid'] = child3.text
elif(child2.tag == ns + 'orcid-bio'):
for child3 in child2:
if(child3.tag == ns + 'personal-details'):
for child4 in child3:
if(child4.tag == ns + 'given-names'):
author['firstname'] = child4.text
elif(child4.tag == ns + 'family-name'):
author['lastname'] = child4.text
elif(child4.tag == ns + 'other-names'):
for child5 in child4:
if(child5.tag == ns + 'other-name'):
author['othernames'].append(child5.text)
elif(child3.tag == ns + 'researcher-urls'):
for child4 in child3:
if(child4.tag == ns + 'researcher-url'):
for child5 in child4:
if(child5.tag == ns + 'url'):
author['urls'].append(child5.text)
elif(child3.tag == ns + 'contact-details'):
for child4 in child3:
if(child4.tag == ns + 'email'):
author['email'] = child4.text
elif(child3.tag == ns + 'external-identifiers'):
for child4 in child3:
if(child4.tag == ns + 'external-identifier'):
identifier = {}
for child5 in child4:
if(child5.tag == ns + 'external-id-common-name'):
key = None
if(child5.text == 'ResearcherID'):
key = 'ResearcherID'
elif(child5.text == 'Scopus Author ID'):
key = 'ScopusID'
elif(child5.tag == ns + 'external-id-reference'):
value = child5.text
if key is not None:
identifier[key] = value
author['identifiers'].append(identifier)
return author
def orcid_author_works_get_parser(orcid):
"""
Method to parse the author works from ORCID website into a dictionary object, given the orcid of the author
"""
out_file = "data/orcid_author_works_get.xml"
fout = open(out_file, "w")
print >> fout, ORCID.orcid_author_works_get(orcid, kind="xml").encode('utf-8')
fout.close()
tree = ET.parse(out_file)
root_element = tree.getroot()
ns = '{http://www.orcid.org/ns/orcid}'
author = {'works': []}
for child1 in root_element:
if(child1.tag == ns + 'orcid-profile'):
for child2 in child1:
if(child2.tag == ns + 'orcid-identifier'):
for child3 in child2:
if(child3.tag == ns + 'path'):
author['orcid'] = child3.text
elif(child2.tag == ns + 'orcid-activities'):
for child3 in child2:
if(child3.tag == ns + 'orcid-works'):
for child4 in child3:
if(child4.tag == ns + 'orcid-work'):
work = {'identifiers': [], 'authorIDs': []}
for child5 in child4:
if(child5.tag == ns + 'work-title'):
for child6 in child5:
if(child6.tag == ns + 'title'):
work['title'] = child6.text
elif(child5.tag == ns + 'journal-title'):
work['journalTitle'] = child5.text
elif(child5.tag == ns + 'work-citation'):
for child6 in child5:
if(child6.tag == ns + 'work-citation-type'):
work['work-citation-type'] = child6.text
elif(child6.tag == ns + 'citation'):
citation = child6.text
if(work['work-citation-type'] == 'bibtex'):
work['authors'] = ORCID_Parser.get_authors_list_from_bibtex(citation)
elif(work['work-citation-type'] == 'formatted-unspecified'):
work['authors'] = ORCID_Parser.get_authors_list_from_unformattedtext(citation)
elif(child5.tag == ns + 'publication-date'):
for child6 in child5:
if(child6.tag == ns + 'year'):
work['year'] = child6.text
elif(child5.tag == ns + 'work-external-identifiers'):
for child6 in child5:
if(child6.tag == ns + 'work-external-identifier'):
identifier = {}
for child7 in child6:
if(child7.tag == ns + 'work-external-identifier-type'):
key = None
if(child7.text == 'doi'):
key = 'doi'
elif(child7.tag == ns + 'work-external-identifier-id'):
value = child7.text
if key is not None:
identifier[key] = value
work[key] = value
work['identifiers'].append(identifier)
if 'title' not in work:
work['title'] = ''
if 'doi' not in work:
publications = IEEE_Parser.ieee_publication_search_parser(work['title'])
if(len(publications) == 1):
for publication in publications:
work['doi'] = publication['doi']
else:
work['doi'] = ''
if 'authors' not in work:
work['authors'] = []
author['works'].append(work)
return author
