diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-01-28 12:52:48 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-01-28 12:52:48 -0800 |
| commit | b9237268c61777a28f5d8e512b326337715aab44 (patch) | |
| tree | 5aef0fbaebedb3ec3be241c61835306631700b5a | |
| parent | 084807ee51f6b5844b323a1217a70b2f12ee966d (diff) | |
| download | sandcrawler-b9237268c61777a28f5d8e512b326337715aab44.tar.gz sandcrawler-b9237268c61777a28f5d8e512b326337715aab44.zip | |
block springer page-one domain
| -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 148abdb..9f07fc3 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -78,6 +78,9 @@ class IngestFileWorker(SandcrawlerWorker): "://jist.net.in", "://croisements-revue.org", + # all stubs/previews, not full papers + "://page-one.live.cf.public.springer.com", + ] def check_existing_ingest(self, base_url): |