diff options
author | Martin Czygan <martin.czygan@gmail.com> | 2020-09-23 00:45:38 +0200 |
---|---|---|
committer | Martin Czygan <martin.czygan@gmail.com> | 2020-09-23 00:45:38 +0200 |
commit | 6589bffcde0ece37f4976553407ee849af7f28b5 (patch) | |
tree | ad89a3c8f56620d341cc35aecbca44f051443d0d /python/tests | |
parent | 5c879f7f147b11d1013772b2f9a74442984f58fc (diff) | |
download | fatcat-6589bffcde0ece37f4976553407ee849af7f28b5.tar.gz fatcat-6589bffcde0ece37f4976553407ee849af7f28b5.zip |
address spammy datacite titles
seemingly from zenodo:
* https://fatcat.wiki/release/rzcpjwukobd4pj36ipla22cnoi
* https://doi.org/10.5281/zenodo.4041777
About 3400 records with "FULL MOVIE" in title, currently.
Diffstat (limited to 'python/tests')
-rw-r--r-- | python/tests/import_datacite.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/python/tests/import_datacite.py b/python/tests/import_datacite.py index ba09ba74..6bc0e7b8 100644 --- a/python/tests/import_datacite.py +++ b/python/tests/import_datacite.py @@ -318,6 +318,12 @@ def test_parse_datacite_dates(): result = parse_datacite_dates(case.input) assert result == case.result, case.about +def test_datacite_spammy_title(datacite_importer): + r = datacite_importer.parse_record({"title": """HD! My Hero academia + Heroes: Rising [2020]Full Movie Watch + Online And Free Download""", + "attributes": {"doi": "10.1234/1234"}}) + assert r == False def test_datacite_importer(datacite_importer): last_index = datacite_importer.api.get_changelog(limit=1)[0].index |