diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/ia.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/python/sandcrawler/ia.py b/python/sandcrawler/ia.py index 9a1b8c8..dbafa01 100644 --- a/python/sandcrawler/ia.py +++ b/python/sandcrawler/ia.py @@ -139,6 +139,10 @@ class CdxApiClient: else: status_code = int(raw[4]) + # CDX rows with no WARC records? + if raw[8] == '-' or raw[9] == '-' or raw[10] == '-': + continue + row = CdxRow( surt=raw[0], datetime=raw[1], |