def _new_nexson_with_crossref_metadata(doi, ref_string, include_cc0=False):
if doi:
# use the supplied DOI to fetch study metadata
search_term = doi
elif ref_string:
# use the supplied reference text to fetch study metadata
search_term = ref_string
# look for matching studies via CrossRef.org API
doi_lookup_response = fetch(
'http://search.crossref.org/dois?%s' %
urlencode({'q': search_term})
)
doi_lookup_response = unicode(doi_lookup_response, 'utf-8') # make sure it's Unicode!
matching_records = anyjson.loads(doi_lookup_response)
# if we got a match, grab the first (probably only) record
if len(matching_records) > 0:
match = matching_records[0];
# Convert HTML reference string to plain text
raw_publication_reference = match.get('fullCitation', '')
ref_element_tree = web2pyHTMLParser(raw_publication_reference).tree
# root of this tree is the complete mini-DOM
ref_root = ref_element_tree.elements()[0]
# reduce this root to plain text (strip any tags)
meta_publication_reference = ref_root.flatten().decode('utf-8')
meta_publication_url = match.get('doi', u'') # already in URL form
meta_year = match.get('year', u'')
else:
# Add a bogus reference string to signal the lack of results
if doi:
meta_publication_reference = u'No matching publication found for this DOI!'
else:
meta_publication_reference = u'No matching publication found for this reference string'
meta_publication_url = u''
meta_year = u''
# add any found values to a fresh NexSON template
nexson = get_empty_nexson(BY_ID_HONEY_BADGERFISH, include_cc0=include_cc0)
nexml_el = nexson['nexml']
nexml_el[u'^ot:studyPublicationReference'] = meta_publication_reference
if meta_publication_url:
nexml_el[u'^ot:studyPublication'] = {'@href': meta_publication_url}
if meta_year:
nexml_el[u'^ot:studyYear'] = meta_year
return nexson
def test_web2pyHTMLParser(self):
#tag should not be a byte
self.assertEqual(web2pyHTMLParser("<div></div>").tree.components[0].tag, 'div')
a = str(web2pyHTMLParser('<div>a<span>b</div>c').tree)
self.assertEqual(a, "<div>a<span>b</span></div>c")
tree = web2pyHTMLParser('hello<div a="b">world</div>').tree
tree.element(_a='b')['_c']=5
self.assertEqual(str(tree), 'hello<div a="b" c="5">world</div>')
a = str(web2pyHTMLParser('<div><img class="img"/></div>', closed=['img']).tree)
self.assertEqual(a, '<div><img class="img" /></div>')
#greater-than sign ( > ) --> decimal > --> hexadecimal >
#Less-than sign ( < ) --> decimal < --> hexadecimal <
# test decimal
a = str(web2pyHTMLParser('<div>< ></div>').tree)
self.assertEqual(a, '<div>< ></div>')
# test hexadecimal
a = str(web2pyHTMLParser('<div>< ></div>').tree)
self.assertEqual(a, '<div>< ></div>')
def test_web2pyHTMLParser(self):
#tag should not be a byte
self.assertEqual(web2pyHTMLParser("<div></div>").tree.components[0].tag, 'div')
a = str(web2pyHTMLParser('<div>a<span>b</div>c').tree)
self.assertEqual(a, "<div>a<span>b</span></div>c")
tree = web2pyHTMLParser('hello<div a="b">world</div>').tree
tree.element(_a='b')['_c']=5
self.assertEqual(str(tree), 'hello<div a="b" c="5">world</div>')
a = str(web2pyHTMLParser('<div><img class="img"/></div>', closed=['img']).tree)
self.assertEqual(a, '<div><img class="img" /></div>')
#greater-than sign ( > ) --> decimal > --> hexadecimal >
#Less-than sign ( < ) --> decimal < --> hexadecimal <
# test decimal
a = str(web2pyHTMLParser('<div>< ></div>').tree)
self.assertEqual(a, '<div>< ></div>')
# test hexadecimal
a = str(web2pyHTMLParser('<div>< ></div>').tree)
self.assertEqual(a, '<div>< ></div>')