def get_authors_by_venue(cached_list, cached_set, cdblp_venue, dblp_venue):
d = DBLPQuery.get_cache('cdblp-pub-cache.data')
if not d.__contains__(cdblp_venue.get('title')):
print('This C-DBLP venue is not on file.')
return
res = urlopen('http://www.dblp.org/search/api/?q=ce:venue:{}:*&h=750&format=json'.format(dblp_venue.get('title').lower()))
# fix titles as { "Title ..." }
fixed_json = re.compile('({\s*)(".+")(\s*})').sub(lambda m: m.group(2), res.read().decode('utf-8'))
# get publications
cdblp_pubs = d.get(cdblp_venue.get('title'))
dblp_pubs = json.loads(fixed_json)
cdblp_authors = set()
dblp_authors = set()
authors = dict()
#print(type(cdblp_pubs))
#print(cdblp_pubs.keys())
for ky in cdblp_pubs.keys():
for ki in cdblp_pubs.get(ky).keys():
for pub in cdblp_pubs.get(ky).get(ki):
for author in pub.get('authors'):
cdblp_authors.add(author)
for pub in dblp_pubs.get('result').get('hits').get('hit'):
try:
for author in pub.get('info').get('authors').get('author'):
dblp_authors.add(author)
except AttributeError:
print('PublicationException: %s' % pub.get('@id'))
pinyin = PinYin()
pinyin.load_word()
for author in cdblp_authors:
name_comp = CDBLPAuthor.get_english_name(author, pinyin)
if name_comp['full_name'] in dblp_authors:
if authors.__contains__(name_comp['full_name']):
authors[name_comp['full_name']]['zh'] = name_comp['zh']
authors[name_comp['full_name']]['count'] += 1
else:
authors[name_comp['full_name']] = { 'zh': name_comp['zh'], 'count': 1 }
elif len(author) == 3 and authors.__contains__(name_comp['full_name_dash']):
if authors.__contains__(name_comp['full_name_dash']):
authors[name_comp['full_name_dash']]['zh'] = name_comp['zh']
authors[name_comp['full_name_dash']]['count'] += 1
else:
authors[name_comp['full_name_dash']] = { 'zh': name_comp['zh'], 'count': 1 }
return authors
