From 21a066496169aa725b20537c2b74d0db67156f57 Mon Sep 17 00:00:00 2001
From: pyr0ball <pyroballpcs@gmail.com>
Date: Thu, 21 May 2026 16:22:26 -0700
Subject: [PATCH] feat(pipeline): weekly Purple Carrot harvest script + cron

Add weekly_harvest.sh wrapper that:
- Runs discover_current_menu.py to fetch this week's 23 active menu slugs
- Runs scrape_live.py with --resume to scrape only new slugs
- Appends timestamped output to /Library/Assets/kiwi/pipeline/logs/

Cron entry added to system crontab:
  0 23 * * 0 (every Sunday 23:00)
Logs: /Library/Assets/kiwi/pipeline/logs/purple_carrot_harvest.log
---
 .../pipeline/purple_carrot/weekly_harvest.sh  | 35 +++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100755 scripts/pipeline/purple_carrot/weekly_harvest.sh

diff --git a/scripts/pipeline/purple_carrot/weekly_harvest.sh b/scripts/pipeline/purple_carrot/weekly_harvest.sh
new file mode 100755
index 0000000..74bf6c8
--- /dev/null
+++ b/scripts/pipeline/purple_carrot/weekly_harvest.sh
@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+# Weekly Purple Carrot recipe harvest
+# Runs every Sunday night via cron.
+# Discovers this week's menu and scrapes full recipe data.
+# Logs to /Library/Assets/kiwi/pipeline/logs/purple_carrot_harvest.log
+
+set -euo pipefail
+
+REPO="/Library/Development/CircuitForge/kiwi"
+MENU_OUT="/Library/Assets/kiwi/pipeline/recipes_purplecarrot_menu.parquet"
+LIVE_OUT="/Library/Assets/kiwi/pipeline/recipes_purplecarrot_live.parquet"
+LOG_DIR="/Library/Assets/kiwi/pipeline/logs"
+LOG="$LOG_DIR/purple_carrot_harvest.log"
+
+mkdir -p "$LOG_DIR"
+
+echo "=== Purple Carrot harvest $(date -u '+%Y-%m-%d %H:%M UTC') ===" >> "$LOG"
+
+cd "$REPO"
+
+# Step 1: discover this week's menu slugs
+echo "[1/2] Discovering current menu slugs..." | tee -a "$LOG"
+conda run -n cf python3 scripts/pipeline/purple_carrot/discover_current_menu.py \
+  --out "$MENU_OUT" 2>&1 | tee -a "$LOG"
+
+# Step 2: scrape full recipe data for new slugs only (--resume skips already-scraped)
+echo "[2/2] Scraping live recipe pages..." | tee -a "$LOG"
+conda run -n cf python3 scripts/pipeline/purple_carrot/scrape_live.py \
+  --slugs-from "$MENU_OUT" \
+  --out "$LIVE_OUT" \
+  --resume \
+  --delay 3.0 2>&1 | tee -a "$LOG"
+
+echo "=== Done $(date -u '+%Y-%m-%d %H:%M UTC') ===" >> "$LOG"
+echo "" >> "$LOG"