diff options
| author | Bryan Newbold <bnewbold@robocracy.org> | 2019-04-22 14:48:30 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@robocracy.org> | 2019-04-22 14:48:30 -0700 |
| commit | e195e3f1f47698d9cae705bbed737b46580bc10f (patch) | |
| tree | e5f46a3c3749586d00d7217c8a731c09c9ee996e | |
| parent | 5ed0fdfecc8e458d2595794b887c5d9b3febef43 (diff) | |
| download | fatcat-e195e3f1f47698d9cae705bbed737b46580bc10f.tar.gz fatcat-e195e3f1f47698d9cae705bbed737b46580bc10f.zip | |
arabesque importer does require timestamp/wayback
| -rw-r--r-- | python/fatcat_tools/importers/arabesque.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/fatcat_tools/importers/arabesque.py b/python/fatcat_tools/importers/arabesque.py index ad211d21..4353795a 100644 --- a/python/fatcat_tools/importers/arabesque.py +++ b/python/fatcat_tools/importers/arabesque.py @@ -120,6 +120,9 @@ class ArabesqueMatchImporter(EntityImporter): if not url: self.counts['skip-url'] += 1 return None + if not row['final_timestamp']: + self.counts['skip-missing-timestamp'] += 1 + return None wayback = "https://web.archive.org/web/{}/{}".format( row['final_timestamp'], row['final_url']) |