python - sandcrawler - [no description]

Mode	Name	Size
-rw-r--r--	.coveragerc	32	log stats plain
-rw-r--r--	.gitignore	29	log stats plain
-rw-r--r--	.pylintrc	409	log stats plain
-rw-r--r--	Pipfile	651	log stats plain
-rw-r--r--	Pipfile.lock	62666	log stats plain
-rw-r--r--	TODO	52	log stats plain
-rw-r--r--	common.py	2618	log stats plain
-rwxr-xr-x	deliver_dumpgrobid_to_s3.py	4092	log stats plain
-rwxr-xr-x	deliver_gwb_to_disk.py	7109	log stats plain
-rwxr-xr-x	deliver_gwb_to_s3.py	7663	log stats plain
-rwxr-xr-x	enrich_scored_matches.py	938	log stats plain
-rwxr-xr-x	filter_grobid_metadata.py	4621	log stats plain
-rwxr-xr-x	filter_groupworks.py	4233	log stats plain
-rwxr-xr-x	filter_scored_matches.py	3432	log stats plain
-rwxr-xr-x	grobid2json.py	5595	log stats plain
-rwxr-xr-x	ia_pdf_match.py	2889	log stats plain
-rwxr-xr-x	import_grobid_metadata.py	2426	log stats plain
-rwxr-xr-x	ingest_file.py	10487	log stats plain
-rwxr-xr-x	kafka_grobid.py	13599	log stats plain
-rwxr-xr-x	manifest_converter.py	1594	log stats plain
-rw-r--r--	pytest.ini	171	log stats plain
d---------	sandcrawler	111	log stats plain
d---------	tests	161	log stats plain
l---------	title_slug_blacklist.txt -> ../scalding/src/main/resources/slug-denylist.txt	48	log stats plain
-rw-r--r--	xml2json.py	199	log stats plain