Avoid problems with percent encoded utf-8 abstracts on certain chinese papers

This commit is contained in:
Ozzie Isaacs 2022-02-12 12:41:29 +01:00
parent 9c5970bbfc
commit 7bb3cac7fb
1 changed files with 2 additions and 2 deletions

View File

@ -17,7 +17,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>. # along with this program. If not, see <http://www.gnu.org/licenses/>.
import itertools import itertools
from typing import Dict, List, Optional from typing import Dict, List, Optional
from urllib.parse import quote from urllib.parse import quote, unquote
try: try:
from fake_useragent.errors import FakeUserAgentError from fake_useragent.errors import FakeUserAgentError
@ -66,7 +66,7 @@ class scholar(Metadata):
) )
match.cover = result.get("image", {}).get("original_url", generic_cover) match.cover = result.get("image", {}).get("original_url", generic_cover)
match.description = result["bib"].get("abstract", "") match.description = unquote(result["bib"].get("abstract", ""))
match.publisher = result["bib"].get("venue", "") match.publisher = result["bib"].get("venue", "")
match.publishedDate = result["bib"].get("pub_year") + "-01-01" match.publishedDate = result["bib"].get("pub_year") + "-01-01"
match.identifiers = {"scholar": match.id} match.identifiers = {"scholar": match.id}