diff options
| -rw-r--r-- | python/sandcrawler/ingest.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py index d2a9980..6d8b162 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -101,6 +101,9 @@ class IngestFileWorker(SandcrawlerWorker): # Historical non-paper content: "dhz.uni-passau.de/", # newspapers "digital.ucd.ie/", # ireland national historical + + # DOI prefixes + "://doi.org/10.2307/", # JSTOR; slow and many redirects ] self.wall_blocklist = [ |