diff options
| -rw-r--r-- | python/fatcat_tools/importers/datacite.py | 19 | ||||
| -rw-r--r-- | python/fatcat_web/templates/container_view.html | 10 | ||||
| -rw-r--r-- | python/fatcat_web/templates/release_view.html | 6 | ||||
| -rw-r--r-- | python/tests/import_datacite.py | 6 |
4 files changed, 33 insertions, 8 deletions
diff --git a/python/fatcat_tools/importers/datacite.py b/python/fatcat_tools/importers/datacite.py index d4ff6784..86740e80 100644 --- a/python/fatcat_tools/importers/datacite.py +++ b/python/fatcat_tools/importers/datacite.py @@ -154,6 +154,15 @@ UNKNOWN_MARKERS = set(DATACITE_UNKNOWN_MARKERS).union(set(( # UNKNOWN_MARKERS_LOWER are lowercase version of UNKNOWN blacklist. UNKNOWN_MARKERS_LOWER = set((v.lower() for v in UNKNOWN_MARKERS)) +# Any "min" number of "tokens" will signal "spam", https://fatcat.wiki/release/rzcpjwukobd4pj36ipla22cnoi +DATACITE_TITLE_SPAM_WORDGROUPS = [ + { + "tokens": ('full', 'movies', 'movie', 'watch', 'streaming', 'online', + 'free', 'hd', 'download', 'english', 'subtitle', 'bluray'), + "min": 4, + } +] + # TODO(martin): merge this with other maps and lookup functions, eventually. LICENSE_SLUG_MAP = { "//archaeologydataservice.ac.uk/advice/termsofuseandaccess.xhtml/": "ADS-UK", @@ -337,6 +346,16 @@ class DataciteImporter(EntityImporter): print('[{}] skipping record w/o title: {}'.format(doi, obj), file=sys.stderr) return False + # check for blacklisted "spam", e.g. "FULL MOVIE" + for rule in DATACITE_TITLE_SPAM_WORDGROUPS: + seen = set() + for token in rule.get("tokens", []): + if token in title.lower(): + seen.add(token) + if len(seen) >= rule.get("min"): + print("[{}] skipping spammy title: {}".format(doi, obj), file=sys.stderr) + return False + if not subtitle: subtitle = None else: diff --git a/python/fatcat_web/templates/container_view.html b/python/fatcat_web/templates/container_view.html index 91430715..32c06a53 100644 --- a/python/fatcat_web/templates/container_view.html +++ b/python/fatcat_web/templates/container_view.html @@ -121,10 +121,10 @@ <i class="icon times grey"></i> Not in <a href="https://road.issn.org">ISSN ROAD</a><br> {% endif %} - {% if container._es.in_kbart == True %} - <i class="icon check green"></i> In <a href="https://thekeepers.org/purl/issn/{{ container.issnl }}">Keepers Registery</a><br> - {% elif container._es.in_kbart == False %} - <i class="icon times grey"></i> Not in <a href="https://thekeepers.org/journals?query={{ container.issnl }}">Keepers Registry</a><br> + {% if container._es.any_kbart == True %} + <i class="icon check green"></i> In <a href="https://keepers.issn.org/?q=api/search&search[]=MUST=allissn={{ container.issnl }}&search[]=MUST_EXIST=keepers">Keepers Registery</a><br> + {% elif container._es.any_kbart == False %} + <i class="icon times grey"></i> Not in <a href="https://keepers.issn.org/?q=api/search&search[]=MUST=allissn={{ container.issnl }}&search[]=MUST_EXIST=keepers">Keepers Registry</a><br> {% endif %} {% if container.extra and container.extra.sherpa_romeo and container.extra.sherpa_romeo.color %} @@ -138,7 +138,7 @@ <div class="content"> {% if container.issnl %} <a href="https://portal.issn.org/resource/issn/{{ container.issnl }}">ISSN Portal</a><br> - <a href="https://thekeepers.org/purl/issn/{{ container.issnl }}">The Keepers Registry</a> (preservation)<br> + <a href="https://keepers.issn.org/?q=api/search&search[]=MUST=allissn={{ container.issnl }}&search[]=MUST_EXIST=keepers">The Keepers Registry</a> (preservation)<br> <a href="http://www.sherpa.ac.uk/romeo/issn/{{ container.issnl }}/">SHERPA/RoMEO</a> (access policies)<br> {% endif %} {% if not container.wikidata_qid %} diff --git a/python/fatcat_web/templates/release_view.html b/python/fatcat_web/templates/release_view.html index f907dab8..54ead411 100644 --- a/python/fatcat_web/templates/release_view.html +++ b/python/fatcat_web/templates/release_view.html @@ -370,9 +370,9 @@ accessible version. {% elif release.container._es.in_road == False %} <i class="icon times grey"></i> Not in <a href="https://road.issn.org">ISSN ROAD</a><br> {% endif %} - {% if release.container._es.in_kbart == True %} - <i class="icon check green"></i> In <a href="https://thekeepers.org/purl/issn/{{ release.container.issnl }}">Keepers Registery</a><br> - {% elif release.container._es.in_kbart == False %} <i class="icon times grey"></i> Not in <a href="https://thekeepers.org/journals?query={{ release.container.issnl }}">Keepers Registry</a><br> + {% if release.container._es.any_kbart == True %} + <i class="icon check green"></i> In <a href="https://keepers.issn.org/?q=api/search&search[]=MUST=allissn={{ release.container.issnl }}&search[]=MUST_EXIST=keepers">Keepers Registery</a><br> + {% elif release.container._es.any_kbart == False %} <i class="icon times grey"></i> Not in <a href="https://keepers.issn.org/?q=api/search&search[]=MUST=allissn={{ release.container.issnl }}&search[]=MUST_EXIST=keepers">Keepers Registry</a><br> {% endif %} {% endif %} {% if release.container.issnl != None %} 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 |