diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-01-17 12:24:42 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-01-17 12:24:42 -0800 |
| commit | 8f5c2ed46b809faad22c8f911ad77be4f8a156f8 (patch) | |
| tree | 083cefaadf9b2253edb140b943bca3e22bd47b14 | |
| parent | 58f744e97c8f3f1a3472aa821f4518d7d139e850 (diff) | |
| download | sandcrawler-8f5c2ed46b809faad22c8f911ad77be4f8a156f8.tar.gz sandcrawler-8f5c2ed46b809faad22c8f911ad77be4f8a156f8.zip | |
add SKIP log line for skip-url-blocklist path
| -rw-r--r-- | python/sandcrawler/ingest.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py index 4732509..38ba55c 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -223,6 +223,7 @@ class IngestFileWorker(SandcrawlerWorker): for block in self.base_url_blocklist: if block in base_url: + print("[SKIP {}\t] {}".format(ingest_type, base_url), file=sys.stderr) return dict(request=request, hit=False, status="skip-url-blocklist") print("[INGEST {}\t] {}".format(ingest_type, base_url), file=sys.stderr) |
