scripts « python - sandcrawler

Mode	Name	Size
-rwxr-xr-x	arabesque2ingestrequest.py	2259	log stats plain
-rwxr-xr-x	archiveorg_fileset.py	3888	log stats plain
-rwxr-xr-x	cdx_collection.py	2151	log stats plain
-rwxr-xr-x	covid2ingestrequest.py	2062	log stats plain
-rwxr-xr-x	deliver_dumpgrobid_to_s3.py	3674	log stats plain
-rwxr-xr-x	deliver_gwb_to_disk.py	7218	log stats plain
-rwxr-xr-x	deliver_gwb_to_s3.py	7783	log stats plain
-rwxr-xr-x	doaj2ingestrequest.py	3773	log stats plain
-rwxr-xr-x	enrich_scored_matches.py	952	log stats plain
-rwxr-xr-x	fetch_cdx_sha1hex.py	4610	log stats plain
-rwxr-xr-x	filter_grobid_metadata.py	4789	log stats plain
-rwxr-xr-x	filter_groupworks.py	4242	log stats plain
-rwxr-xr-x	filter_scored_matches.py	3442	log stats plain
-rwxr-xr-x	grobid_affiliations.py	1644	log stats plain
-rwxr-xr-x	import_grobid_metadata.py	2410	log stats plain
-rwxr-xr-x	ingestrequest_row2json.py	1422	log stats plain
-rwxr-xr-x	manifest_converter.py	1599	log stats plain
-rwxr-xr-x	oai2ingestrequest.py	3541	log stats plain
-rwxr-xr-x	pdf_thumbnail.py	954	log stats plain
-rwxr-xr-x	unpaywall2ingestrequest.py	2864	log stats plain