diff options
author | Bryan Newbold <bnewbold@archive.org> | 2022-02-08 16:57:16 -0800 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2022-02-08 16:57:16 -0800 |
commit | b76630806d43427ddcdef8cd6efd110c731668a5 (patch) | |
tree | 2b0d9c940ab6abc13ed36e4c4ecf0a4011ba5426 /sql/dump_reingest_bulk.sql | |
parent | 963fc4a50e0eddc99c14c6ff571d099e8873abac (diff) | |
download | sandcrawler-b76630806d43427ddcdef8cd6efd110c731668a5.tar.gz sandcrawler-b76630806d43427ddcdef8cd6efd110c731668a5.zip |
sql: script to reingest recent spn2 lookup failure in bulk mode
Diffstat (limited to 'sql/dump_reingest_bulk.sql')
-rw-r--r-- | sql/dump_reingest_bulk.sql | 25 |
1 files changed, 25 insertions, 0 deletions
diff --git a/sql/dump_reingest_bulk.sql b/sql/dump_reingest_bulk.sql new file mode 100644 index 0000000..403fb20 --- /dev/null +++ b/sql/dump_reingest_bulk.sql @@ -0,0 +1,25 @@ + +COPY ( + SELECT row_to_json(ingest_request.*) FROM ingest_request + LEFT JOIN ingest_file_result ON ingest_file_result.base_url = ingest_request.base_url + WHERE + (ingest_request.ingest_type = 'pdf' + OR ingest_request.ingest_type = 'html') + AND ingest_file_result.hit = false + AND ingest_request.created < NOW() - '24 hour'::INTERVAL + AND ingest_request.created > NOW() - '181 day'::INTERVAL + AND (ingest_request.ingest_request_source = 'fatcat-changelog' + OR ingest_request.ingest_request_source = 'fatcat-ingest') + AND ( + ingest_file_result.status like 'spn2-%' + OR ingest_file_result.status like 'cdx-error' + OR ingest_file_result.status like 'petabox-error' + ) + AND ingest_file_result.status != 'spn2-error:invalid-url-syntax' + AND ingest_file_result.status != 'spn2-error:filesize-limit' + AND ingest_file_result.status != 'spn2-error:not-found' + AND ingest_file_result.status != 'spn2-error:blocked-url' + AND ingest_file_result.status != 'spn2-error:too-many-redirects' + AND ingest_file_result.status != 'spn2-error:network-authentication-required' + AND ingest_file_result.status != 'spn2-error:unknown' +) TO '/srv/sandcrawler/tasks/reingest_bulk_current.rows.json'; |