diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2021-10-28 14:55:14 +0200 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2021-10-28 14:55:14 +0200 |
| commit | f175ef84d070b8c6ab231836e469d7d5d1b81c28 (patch) | |
| tree | 6dc475649baf2a100960c794313fba8bf5bfe40d | |
| parent | d8dfa06ee9694655df3f51823deff4e9a63971c6 (diff) | |
| download | refcat-f175ef84d070b8c6ab231836e469d7d5d1b81c28.tar.gz refcat-f175ef84d070b8c6ab231836e469d7d5d1b81c28.zip | |
tasks: fix json key
| -rw-r--r-- | python/refcat/tasks.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 4265050..d42bfa5 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -1552,9 +1552,11 @@ class UnmatchedRefsReparse(Refcat): if i % 100000 == 0: self.logger.debug("@{}".format(i)) doc = json.loads(line) - if not "unstructured" in doc: + if not "biblio" in doc: continue - unstructured = doc["unstructured"] + if not "unstructured" in doc["biblio"]: + continue + unstructured = doc["biblio"]["unstructured"] if len(unstructured) < 5: continue grobid_resp = requests.post( |