diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/ingest_file.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/python/sandcrawler/ingest_file.py b/python/sandcrawler/ingest_file.py index 4ec37c1..11f2df9 100644 --- a/python/sandcrawler/ingest_file.py +++ b/python/sandcrawler/ingest_file.py @@ -153,6 +153,8 @@ class IngestFileWorker(SandcrawlerWorker): "doi.org/10.15468/", # gbif.org: database entry # deprecated domain (doesn't redirect correctly) "://edoc.mpg.de/", + # bogus/spam PDFs + "://isiarticles.com/", ] self.wall_blocklist = [ |