Enhance crawler with seed list and SQL utilities

Add seedList module for URL initialization, comprehensive SQL utilities for database analysis, and update project configuration.
This commit is contained in:
antanst
2025-06-16 12:29:33 +03:00
parent 51f94c90b2
commit 330b596497
37 changed files with 742 additions and 682 deletions

View File

@@ -0,0 +1,8 @@
-- File: snapshots_per_url.sql
-- Basic count of snapshots per URL
-- Usage: \i misc/sql/snapshots_per_url.sql
SELECT url, COUNT(*) as snapshot_count
FROM snapshots
GROUP BY url
ORDER BY snapshot_count DESC;