diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 21:01:25 -0800 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 21:01:25 -0800 |
commit | 1b74e8a4dee21bd260040dad8072e4fb48456b3c (patch) | |
tree | 36a5c8f263ff7a1637754816c0d76a226e77532d /sql/stats/README.md | |
parent | be8f1d134681caaa15485246b65551a67e5bd5a5 (diff) | |
download | sandcrawler-1b74e8a4dee21bd260040dad8072e4fb48456b3c.tar.gz sandcrawler-1b74e8a4dee21bd260040dad8072e4fb48456b3c.zip |
recent sandcrawler-db / ingest stats (interesting)
Diffstat (limited to 'sql/stats/README.md')
-rw-r--r-- | sql/stats/README.md | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/sql/stats/README.md b/sql/stats/README.md index ea61fa0..52642f6 100644 --- a/sql/stats/README.md +++ b/sql/stats/README.md @@ -41,6 +41,10 @@ Total and unique-by-sha1 counts: SELECT COUNT(DISTINCT sha1hex) as unique_sha1, COUNT(*) as total FROM cdx; +mimetype counts: + + SELECT mimetype, COUNT(*) FROM cdx GROUP BY mimetype ORDER BY COUNT(*) DESC; + Processed or not: # TODO: @@ -71,6 +75,8 @@ Requests by source: SELECT ingest_type, link_source, COUNT(*) FROM ingest_request GROUP BY ingest_type, link_source ORDER BY COUNT DESC LIMIT 25; + SELECT ingest_type, link_source, ingest_request_source, COUNT(*) FROM ingest_request GROUP BY ingest_type, link_source, ingest_request_source ORDER BY COUNT DESC LIMIT 25; + Uncrawled requests by source: # TODO: verify this? |