diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/ia.py | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/python/sandcrawler/ia.py b/python/sandcrawler/ia.py index 672a0b6..3ab4971 100644 --- a/python/sandcrawler/ia.py +++ b/python/sandcrawler/ia.py @@ -219,6 +219,11 @@ class CdxApiClient: if raw[5].startswith("sha-256"): continue + # remove CDX rows with 'error' digests + # TODO: follow-up on this (2022-11-01 sandcrawler errors) + if raw[5].lower() == "error": + continue + row = CdxRow( surt=raw[0], datetime=raw[1], |