From 55a00912586a2aea705687472578dc9e8486be5e Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 6 Sep 2019 16:53:21 -0700 Subject: use newer fatcat contianer dump --- chocula.py | 2 +- data/fetch.sh | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/chocula.py b/chocula.py index 12b7ae1..aab4fc3 100755 --- a/chocula.py +++ b/chocula.py @@ -82,7 +82,7 @@ EZB_FILE = 'data/ezb_metadata.json' GOLD_OA_FILE = 'data/ISSN_Gold-OA_3.0.csv' WIKIDATA_SPARQL_FILE = 'data/wikidata_journals_sparql.2019-07-30.tsv' OPENAPC_FILE = 'data/apc_de.2019-07-30.csv' -FATCAT_CONTAINER_FILE = 'data/container_export.2019-08-27.json' +FATCAT_CONTAINER_FILE = 'data/container_export.2019-09-03.json' FATCAT_STATS_FILE = 'data/container_stats.json' diff --git a/data/fetch.sh b/data/fetch.sh index 7d3e805..182953d 100755 --- a/data/fetch.sh +++ b/data/fetch.sh @@ -49,3 +49,5 @@ wget -c https://archive.org/download/wikidata-journal-metadata/wikidata_journals wget -c https://archive.org/download/chocula-journal-counts/url_status.2019-07-31.partial-ia.json wget -c https://archive.org/download/chocula-journal-counts/url_status.2019-07-31.partial-robocracy.json +wget -c https://archive.org/download/fatcat_bulk_exports_2019-07-07/container_export.2019-09-03.json.gz +zcat container_export.2019-09-03.json.gz > container_export.2019-09-03.json -- cgit v1.2.3