def get_doi_el(wiki, dbcnf):
""" Set of DOI codes from external links. """
dois = set([])
doiquery = """SELECT el_to
FROM externallinks
WHERE el_index LIKE 'https://org.doi.dx./10%'
OR el_index LIKE 'http://org.doi.dx./10%'"""
with get_connection(wiki, dbcnf) as connection:
cursor = connection.cursor()
cursor.execute(doiquery)
for link in cursor.fetchall():
try:
doi = re.findall('10.+$', link[0].decode('utf-8'))[0]
if doi:
dois.add(unquote(doi))
except IndexError:
continue
# print "Found %d DOI external links on %s" % (len(dois), wiki)
return dois
评论列表
文章目录