phase 17: enrich SEC EDGAR filings with URLs, titles, dedupe by accession number, skip XML fragments

2026-04-12 09:42:12 -07:00
parent 28b3361833
commit 311d76dc0b
3 changed files with 96 additions and 7 deletions
@@ -0,0 +1,11 @@
+import redis, os
+r = redis.from_url(f"redis://:{os.environ.get('REDIS_PASSWORD','')}@{os.environ['REDIS_HOST']}:{os.environ['REDIS_PORT']}/0")
+for q in ["ingestion","parsing","extraction","aggregation","recommendation","lake_publish","broker_orders"]:
+    depth = r.llen(f"stonks:queue:{q}")
+    print(f"  {q:20} {depth:>4} pending")
+
+# Check dead letter queues
+for q in ["ingestion","parsing","extraction","aggregation","recommendation"]:
+    depth = r.llen(f"stonks:dlq:{q}")
+    if depth > 0:
+        print(f"  DLQ {q:16} {depth:>4} dead letters")