diff options
Diffstat (limited to 'python/fatcat_tools/importers/ingest.py')
-rw-r--r-- | python/fatcat_tools/importers/ingest.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/python/fatcat_tools/importers/ingest.py b/python/fatcat_tools/importers/ingest.py index cd3d53f6..04ff8db6 100644 --- a/python/fatcat_tools/importers/ingest.py +++ b/python/fatcat_tools/importers/ingest.py @@ -86,7 +86,7 @@ class IngestFileResultImporter(EntityImporter): self.counts['skip-ingest_request_source'] += 1 return False - if row['request'].get('link_source') not in ('arxiv', 'pmc', 'unpaywall', 'doi', 'mag', 's2', 'doaj'): + if row['request'].get('link_source') not in ('arxiv', 'pmc', 'unpaywall', 'doi', 'mag', 's2', 'doaj', 'dblp'): self.counts['skip-link-source'] += 1 return False @@ -437,7 +437,9 @@ class IngestWebResultImporter(IngestFileResultImporter): if 'revisit_cdx' in row: terminal_cdx = row['revisit_cdx'] assert terminal_cdx['surt'] - assert terminal_cdx['url'] == terminal['terminal_url'] + if terminal_cdx['url'] != terminal['terminal_url']: + self.counts['skip-terminal-url-mismatch'] += 1 + return None wc_cdx = [] # primary resource first |