diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-05-17 21:11:31 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-05-17 21:11:31 -0700 |
| commit | 9c51894168032a40f2b595208db0ded0baee24bb (patch) | |
| tree | ca2668367c20d0ac6e880254c2768eba146ec760 /extra | |
| parent | 84412e78ee7187a1be36a9058284084c231a0357 (diff) | |
| download | fatcat-scholar-9c51894168032a40f2b595208db0ded0baee24bb.tar.gz fatcat-scholar-9c51894168032a40f2b595208db0ded0baee24bb.zip | |
sitemaps: remove date from sitmap URLs
Diffstat (limited to 'extra')
| -rw-r--r-- | extra/sitemap/README.md | 3 | ||||
| -rwxr-xr-x | extra/sitemap/work_urls_query.sh | 6 |
2 files changed, 2 insertions, 7 deletions
diff --git a/extra/sitemap/README.md b/extra/sitemap/README.md index 6c03095..055575f 100644 --- a/extra/sitemap/README.md +++ b/extra/sitemap/README.md @@ -5,8 +5,7 @@ Requires [fatcat-cli](https://gitlab.com/bnewbold/fatcat-cli) and `jq` installed. Run these commands on a production machine. cd /srv/fatcat_scholar/sitemap - export DATE=`date --iso-8601` - /srv/fatcat_scholar/src/extra/sitemap/work_urls_query.sh $DATE + /srv/fatcat_scholar/src/extra/sitemap/work_urls_query.sh /srv/fatcat_scholar/src/extra/sitemap/generate_sitemap_indices.py ## Background diff --git a/extra/sitemap/work_urls_query.sh b/extra/sitemap/work_urls_query.sh index 98475ff..32ccc11 100755 --- a/extra/sitemap/work_urls_query.sh +++ b/extra/sitemap/work_urls_query.sh @@ -4,10 +4,6 @@ set -e # fail on error set -u # fail if variable not set in substitution set -o pipefail # fail if part of a '|' command fails -: ${1?' You you did not supply a date argument'} - -# eg, 2020-08-19 -DATE="$1" # query for specific works; about 8.6 million circa 2021-04-29 fatcat-cli search scholar 'doc_type:work (fulltext.access_type:ia_file OR fulltext.access_type:wayback) (NOT biblio.arxiv_id:*) (NOT biblio.pmcid:*) (NOT biblio.publisher_type:big5) (year:<1926 OR tags:*)' --index-json --limit 0 \ @@ -15,4 +11,4 @@ fatcat-cli search scholar 'doc_type:work (fulltext.access_type:ia_file OR fullte | jq .key -r \ | tr '_' '/' \ | awk '{print "https://scholar.archive.org/" $1}' \ - | split --lines 20000 - sitemap-works-$DATE- -d -a 5 --additional-suffix .txt + | split --lines 20000 - sitemap-works- -d -a 5 --additional-suffix .txt |