diff options
Diffstat (limited to 'python')
| -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 d63baff..58f3783 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -70,6 +70,9 @@ class IngestFileWorker(SandcrawlerWorker): self.try_spn2 = kwargs.get('try_spn2', True) self.base_url_blocklist = [ + # robot blocking + "://hkvalidate.perfdrive.com/", + # temporary, until we implement specific fetch and 'petabox' output "://archive.org/", "://web.archive.org/web/", |