X-Git-Url: https://code.communitydata.science/covid19.git/blobdiff_plain/a3e40a072f09f5faee5b12df27f313f75d087f3a..974dc48b12aed59fb5bf4ffdd41a6a00e5f5aa47:/cron-wikipedia_revisions.sh diff --git a/cron-wikipedia_revisions.sh b/cron-wikipedia_revisions.sh new file mode 100644 index 0000000..5ba02ed --- /dev/null +++ b/cron-wikipedia_revisions.sh @@ -0,0 +1,17 @@ +#!/bin/bash -x + +TZ="UTC" +date_string=$(date +%Y%m%d) + +revs_log="enwp-revisions-${date_string}.log" +./wikipedia/scripts/wikiproject_scraper.py 2> >(tee wikipedia/logs/${revs_log}) + +./wikipedia/scripts/fetch_enwiki_revisions.py 2> >(tee -a wikipedia/logs/${revs_log}) +mv wikipedia/logs/${revs_log} /var/www/covid19/wikipedia/logs/ + +revs_tsv="digobs_covid19-wikipedia-enwiki_revisions-${date_string}.tsv" +mv wikipedia/data/${revs_tsv} /var/www/covid19/wikipedia + +revs_json="digobs_covid19-wikipedia-enwiki_revisions-${date_string}.json" +xz wikipedia/data/${revs_json} +mv wikipedia/data/${revs_json}.xz /var/www/covid19/wikipedia