handle case where warc record id is missing

... from trough dedup. Not sure why this error happened but we shouldn't
need that field anyway.
This commit is contained in:
Noah Levitt 2018-01-19 14:38:54 -08:00
parent 4b53c10132
commit 57abab100c

View File

@ -419,7 +419,7 @@ class TroughDedupDb(DedupDb):
len(digest_keys), len(results))
assert len(results) >= 0 and len(results) <= len(digest_keys)
for result in results:
result['id'] = result['id'].encode('ascii')
result['id'] = result.get('id') and result['id'].encode('ascii')
result['url'] = result['url'].encode('ascii')
result['date'] = result['date'].encode('ascii')
result['digest_key'] = result['digest_key'].encode('ascii')