mirror of
https://github.com/nubenetes/awesome-kubernetes.git
synced 2026-07-12 09:51:00 +00:00
4e87c248fd
- Add 26-category news digest engine (src/news_digest.py) with Gemini AI ranking for 3/6/12 month temporal panels across tech, cloud, and geo categories - Add discovered_at, company, geo_region fields to inventory schema with backfill script populating 18K+ existing entries - Fix critical v2-mkdocs.yml bug: plugins were nested under theme (silently disabled) - Add MkDocs Material features: instant nav, breadcrumbs, footer, announce bar - Add trending cards CSS grid and replace Agentic Pulse with dynamic Trending Now - Generate tech-digest.md and industry-digest.md with tabbed 3/6/12 month views - Merge 12 stub pages (<40 lines each) into parent categories with redirects - Replace 50 bare except:pass patterns with contextual logging across all pipeline files - Expand autonomous discovery from 6 to 14 GitHub search queries - Add stale health re-check for online entries older than 30 days - Track addition_method by source type (rss, twitter, github_trending) - Add digest generation step to CI publish workflow Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
60 lines
1.8 KiB
Python
60 lines
1.8 KiB
Python
"""
|
|
Backfill script: adds discovered_at to inventory entries that lack it.
|
|
Priority: gh_pushed > last_checked > year > default "2024-01-01T00:00:00"
|
|
Run once: python -m scripts.backfill_discovered_at
|
|
"""
|
|
import sys
|
|
import os
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
|
|
from datetime import datetime
|
|
from src.inventory_manager import load_inventory, save_inventory
|
|
from src.config import MADRID_TZ
|
|
|
|
|
|
def backfill():
|
|
inv = load_inventory()
|
|
updated = 0
|
|
total = 0
|
|
|
|
for url, entry in inv.items():
|
|
if not isinstance(entry, dict):
|
|
continue
|
|
total += 1
|
|
if entry.get("discovered_at"):
|
|
continue
|
|
|
|
discovered = None
|
|
|
|
gh_pushed = entry.get("gh_pushed")
|
|
if gh_pushed and isinstance(gh_pushed, str) and len(gh_pushed) >= 10:
|
|
discovered = gh_pushed
|
|
|
|
if not discovered:
|
|
last_checked = entry.get("last_checked")
|
|
if isinstance(last_checked, (int, float)) and last_checked > 0:
|
|
try:
|
|
discovered = datetime.fromtimestamp(last_checked, tz=MADRID_TZ).isoformat()
|
|
except (OSError, ValueError):
|
|
pass
|
|
|
|
if not discovered:
|
|
year = entry.get("year", "")
|
|
if isinstance(year, str) and year.isdigit() and len(year) == 4:
|
|
discovered = f"{year}-06-01T00:00:00+02:00"
|
|
elif isinstance(year, int):
|
|
discovered = f"{year}-06-01T00:00:00+02:00"
|
|
|
|
if not discovered:
|
|
discovered = "2024-01-01T00:00:00+02:00"
|
|
|
|
entry["discovered_at"] = discovered
|
|
updated += 1
|
|
|
|
print(f"Backfill complete: {updated}/{total} entries updated with discovered_at")
|
|
save_inventory(inv)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
backfill()
|