From 0afb1e361fcc601bf2a0f0fe2ea69f6ae8bd14fd Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 18 May 2021 11:38:49 -0700 Subject: sitemaps: pdfs -> access --- extra/sitemap/pdf_urls_query.sh | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100755 extra/sitemap/pdf_urls_query.sh (limited to 'extra/sitemap/pdf_urls_query.sh') diff --git a/extra/sitemap/pdf_urls_query.sh b/extra/sitemap/pdf_urls_query.sh deleted file mode 100755 index fb1a4b8..0000000 --- a/extra/sitemap/pdf_urls_query.sh +++ /dev/null @@ -1,14 +0,0 @@ -#!/usr/bin/env bash - -set -e # fail on error -set -u # fail if variable not set in substitution -set -o pipefail # fail if part of a '|' command fails - - -# 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 \ - | pv -l \ - | jq '[.fulltext.access_type, .fulltext.access_url] | @tsv' -r \ - | rg -v '^null' \ - | ./transform_access_url.py \ - | split --lines 20000 - sitemap-pdfs- -d -a 5 --additional-suffix .txt -- cgit v1.2.3