Switch menu source from Nutrislice to Claude-read PDF, weekly to monthly pull

The district discontinued Nutrislice in favor of a monthly PDF calendar
per grade band on kyrene.org. That PDF is a graphic calendar grid, not
reliably text-extractable, so scraper.py now sends it to Claude (vision +
structured JSON output) instead of hitting a JSON API. Fetches through a
stable Finalsite resource-manager permalink that always redirects to
whichever month is currently published, so no code change is needed each
month.

Also moves the pull schedule from weekly (day-of-week list) to monthly
(day-of-month), since the source itself is now monthly — defaults to the
25th, since the district tends to post next month's PDF a few days early.

Requires a new ANTHROPIC_API_KEY in the server's .env.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013RbBoYm23muVyMZ18Ldqa6

scraper.py

@@ -1,51 +1,93 @@
+import base64
+import json
 import logging
-from datetime import datetime
 
+import anthropic
 import requests
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
 log = logging.getLogger(__name__)
 
-SCHOOL_SLUG = "kyrene-de-la-mariposa"
-MENU_TYPE = "lunch"
-API_BASE = "https://kyrene.api.nutrislice.com/menu/api/weeks/school"
+# Stable Finalsite "resource manager" permalink for the K-5 lunch menu, found
+# on https://www.kyrene.org/family-student-resources/food-services/school-menus.
+# This URL itself never changes — it 302-redirects to whichever monthly PDF
+# is currently published (verified 2026-09-08: it pointed straight at that
+# month's file). Nutrislice, the previous data source, was discontinued by
+# the district.
+MENU_PAGE_URL = "https://www.kyrene.org/fs/resource-manager/view/32bb3f8b-5a50-4b38-ad68-a5d3108de571"
+
+MODEL = "claude-opus-5"
+
+_MENU_SCHEMA = {
+    "type": "object",
+    "properties": {
+        "days": {
+            "type": "array",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "date": {"type": "string", "description": "ISO date, YYYY-MM-DD"},
+                    "items": {"type": "array", "items": {"type": "string"}},
+                },
+                "required": ["date", "items"],
+                "additionalProperties": False,
+            },
+        },
+    },
+    "required": ["days"],
+    "additionalProperties": False,
+}
+
+_PROMPT = """This PDF is a school cafeteria's monthly lunch calendar (grades K-5). It's a
+calendar-grid layout with one cell per school day, each listing a Breakfast
+section and a Lunch section.
+
+Extract ONLY the Lunch items (ignore Breakfast) for every day of the month
+shown on the calendar. For each day 1 through the last day of the month:
+- If the calendar shows lunch items for that day, list them.
+- If the day has no cafeteria menu (weekend, holiday, or a no-school day
+  like a break), return an empty items list for that date.
+
+Read the month and year printed on the calendar itself to build the ISO
+dates. Return every calendar day of the month, in date order."""
 
 
-def _fetch_week(date_str: str) -> dict:
-    dt = datetime.strptime(date_str, "%Y-%m-%d")
-    url = f"{API_BASE}/{SCHOOL_SLUG}/menu-type/{MENU_TYPE}/{dt.year}/{dt.month:02d}/{dt.day:02d}/"
-    log.info(f"Fetching {url}")
-
-    resp = requests.get(
-        url,
-        headers={"Accept": "application/json", "User-Agent": "Mozilla/5.0"},
-        timeout=20,
-    )
+def _fetch_current_pdf() -> bytes:
+    resp = requests.get(MENU_PAGE_URL, timeout=20)
     resp.raise_for_status()
-    return resp.json()
+    return resp.content
 
 
-def _extract_items(day: dict) -> list[str]:
-    items = []
-    for entry in day.get("menu_items", []):
-        if entry.get("is_section_title") or entry.get("is_station_header"):
-            continue
-        food = entry.get("food")
-        if food and food.get("name"):
-            items.append(food["name"].strip())
-    return items
+def get_month_menu() -> list[dict]:
+    """Fetches whichever monthly K-5 lunch menu PDF is currently published
+    and asks Claude to read it into structured per-day data. Returns
+    [{"date": "YYYY-MM-DD", "items": [...]}, ...] for every day of that
+    month — days with no posted menu (weekends, breaks, holidays) come back
+    with an empty items list, same contract the old Nutrislice-based scraper
+    used."""
+    log.info(f"Fetching {MENU_PAGE_URL}")
+    pdf_b64 = base64.standard_b64encode(_fetch_current_pdf()).decode("utf-8")
 
+    client = anthropic.Anthropic()
+    response = client.messages.create(
+        model=MODEL,
+        max_tokens=8000,
+        messages=[{
+            "role": "user",
+            "content": [
+                {
+                    "type": "document",
+                    "source": {
+                        "type": "base64",
+                        "media_type": "application/pdf",
+                        "data": pdf_b64,
+                    },
+                },
+                {"type": "text", "text": _PROMPT},
+            ],
+        }],
+        output_config={"format": {"type": "json_schema", "schema": _MENU_SCHEMA}},
+    )
 
-def get_week_menu(date_str: str | None = None) -> list[dict]:
-    """Returns every day in the school-published week containing date_str,
-    as [{"date": "YYYY-MM-DD", "items": [...]}, ...] in the API's own order.
-    Days with no posted menu (weekends, breaks, holidays) have an empty items list."""
-    if date_str is None:
-        date_str = datetime.now().strftime("%Y-%m-%d")
-
-    data = _fetch_week(date_str)
-    return [
-        {"date": day.get("date"), "items": _extract_items(day)}
-        for day in data.get("days", [])
-        if day.get("date")
-    ]
+    text = next(b.text for b in response.content if b.type == "text")
+    return json.loads(text)["days"]