def get_dblp_author_from_zh(author_name):
author_cdblp = CDBLPAuthor(author_name)
author_name_comp = CDBLPAuthor.getEnglishName(author_name)
urlpt = '{}/{}:{}'.format(author_name_comp['last_name'][0].lower(), author_name_comp['last_name'], author_name_comp['first_name'])
candidate_urlpts = set()
candidate_authors = []
res = urlopen(DBLPQuery.get_dblp_url(urlpt))
dom = BeautifulSoup(res)
for cu_tag in dom.find_all('li', 'homonym'):
cu = cu_tag.find('a')['href'][3:-5]
candidate_urlpts.add(cu)
if len(candidate_urlpts) == 0:
candidate_urlpts.add(urlpt)
for cu in candidate_urlpts:
author = DBLPAuthor(cu)
candidate_authors.append(author)
print(cu)
# for example, '骞雅楠' => 'Ya-nan Qian' in DBLP
if len(candidate_authors) == 0 and len(author_name) == 3:
res = urlopen('{}/search/author?xauthor={}'.format(DBLPQuery.base_url, quote(author_name_comp['full_name_dash'])))
dom = BeautifulSoup(res)
author_tags = dom.find_all('author')
for author_tag in author_tags:
if author_tag.string == author_name_comp['full_name_dash']:
author = DBLPAuthor(author_tag['urlpt'])
candidate_authors.append(author)
try:
target_author = candidate_authors[0]
except IndexError:
return { 'cdblp': author_cdblp.get_author(), 'dblp': {} }
coauthors_set_cdblp = set(map(lambda a: a['full_name'], author_cdblp.get_coauthors()))
coauthors_set_dblp = set(candidate_authors[0].get_coauthors())
coauthor_count_max = len(set(coauthors_set_cdblp.intersection(coauthors_set_dblp)))
overlap = coauthors_set_cdblp.intersection(coauthors_set_dblp)
if len(candidate_authors) > 1:
for candidate in candidate_authors:
coauthors_set_dblp = set(candidate.get_coauthors())
coauthor_overlap = coauthors_set_cdblp.intersection(coauthors_set_dblp)
if len(coauthor_overlap) >= coauthor_count_max:
target_author = candidate
overlap = coauthor_overlap
else:
target_author = candidate_authors[0]
#print(overlap)
if coauthor_count_max == 0:
return { 'cdblp': author_cdblp.get_author(), 'dblp': {} }
return { 'cdblp': author_cdblp.get_author(), 'dblp': target_author.get_author() }
def author_distinct(cached_list, cached_set, author_name):
trial = author_name[0]
if author_name in cached_set:
d = DBLPQuery.get_cache('author-entries-cache.data')
print('This is a CDBLP author w/ a English name on file.')
author_name_zh = ''
for author_name_comp in cached_list:
if author_name_comp['full_name'] == author_name.strip() or author_name_comp['zh'] == author_name:
author_name_zh = author_name_comp['zh']
break
return {
'cdblp': d.get(author_name_zh, {}),
'dblp': DBLPAuthor('{}/{}:{}'.format(author_name_comp['last_name'][0].lower(), author_name_comp['last_name'], author_name_comp['first_name'])).get_author()
}
else:
if 0x3400 < ord(trial) < 0x2b6f8:
print('This is a CDBLP author w/ a Chinese name.')
author_cdblp = CDBLPAuthor(author_name)
author_name_comp = CDBLPAuthor.getEnglishName(author_name)
res = urlopen('{}/search/author?xauthor={}'.format(DBLPQuery.base_url, quote(author_name_comp['full_name'])))
dom = BeautifulSoup(res)
candidate_authors = []
author_tags = dom.find_all('author')
for author_tag in author_tags:
if author_tag.string == author_name_comp['full_name']:
author = DBLPAuthor(author_tag['urlpt'])
candidate_authors.append(author)
# for example, '骞雅楠' => 'Ya-nan Qian' in DBLP
if len(candidate_authors) == 0 and len(author_name) == 3:
res = urlopen('{}/search/author?xauthor={}'.format(DBLPQuery.base_url, quote(author_name_comp['full_name_dash'])))
dom = BeautifulSoup(res)
author_tags = dom.find_all('author')
for author_tag in author_tags:
if author_tag.string == author_name_comp['full_name_dash']:
author = DBLPAuthor(author_tag['urlpt'])
candidate_authors.append(author)
try:
target_author = candidate_authors[0]
except IndexError:
return { 'cdblp': author_cdblp.get_author(), 'dblp': {} }
coauthors_set_cdblp = set(map(lambda a: a['full_name'], author_cdblp.get_coauthors()))
coauthors_set_dblp = set(candidate_authors[0].get_coauthors())
coauthor_count_max = len(set(coauthors_set_cdblp.intersection(coauthors_set_dblp)))
overlap = coauthors_set_cdblp.intersection(coauthors_set_dblp)
if len(candidate_authors) > 1:
for candidate in candidate_authors:
coauthors_set_dblp = set(candidate.get_coauthors())
coauthor_overlap = coauthors_set_cdblp.intersection(coauthors_set_dblp)
if len(coauthor_overlap) >= coauthor_count_max:
target_author = candidate
overlap = coauthor_overlap
else:
target_author = candidate_authors[0]
#print(overlap)
return { 'cdblp': author_cdblp.get_author(), 'dblp': target_author.get_author() }
else:
print('This is a non-CDBLP author.')
candidates = []
res = urlopen('{}/search/author?xauthor={}'.format(DBLPQuery.base_url, quote(author_name)))
dom = BeautifulSoup(res)
for candidate_tag in dom.find_all('author'):
if author_name == candidate_tag.string:
candidates.append(DBLPAuthor(candidate_tag['urlpt']))
return { 'cdblp': {}, 'dblp': candidates[0].get_author() }
