From 2e3706ad6005366a4084731a7a33db7b800f7bfe Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 20 Apr 2022 16:15:07 -0700 Subject: fix some more isiarticles (with :80 in URL) --- extra/bulk_edits/2022-04-20_isiarticles.md | 13 +++++++++++++ extra/cleanups/file_isiarticles.md | 5 +++++ 2 files changed, 18 insertions(+) (limited to 'extra') diff --git a/extra/bulk_edits/2022-04-20_isiarticles.md b/extra/bulk_edits/2022-04-20_isiarticles.md index ca2cc6f9..b0177a46 100644 --- a/extra/bulk_edits/2022-04-20_isiarticles.md +++ b/extra/bulk_edits/2022-04-20_isiarticles.md @@ -24,3 +24,16 @@ The full batch: | rg 'isiarticles.com/' \ | pv -l \ | fatcat-cli batch update file release_ids= content_scope=sample --description 'Un-link and mark isiarticles PDFs as content_scope=sample' --auto-accept + +And some more with ':80' in the URL: + + fatcat-cli search file domain:isiarticles.com '!content_scope:*' --entity-json -n0 \ + | rg -v '"content_scope"' \ + | rg 'isiarticles.com:80/' \ + | pv -l \ + | fatcat-cli batch update file release_ids= content_scope=sample --description 'Un-link and mark isiarticles PDFs as content_scope=sample' --auto-accept + +Verify: + + fatcat-cli search file domain:isiarticles.com '!content_scope:*' --count + 0 diff --git a/extra/cleanups/file_isiarticles.md b/extra/cleanups/file_isiarticles.md index cb3785af..3858361c 100644 --- a/extra/cleanups/file_isiarticles.md +++ b/extra/cleanups/file_isiarticles.md @@ -13,3 +13,8 @@ get auto-ingested in the future. ## Prod Cleanup See bulk edits log. + +Verify cleanup: + + fatcat-cli search file domain:isiarticles.com '!content_scope:*' --count + 0 -- cgit v1.2.3