commit 4398abd9e6c9c5e25fb79c5829b10221aa0cc42f
Author: LockeShor <75901583+LockeShor@users.noreply.github.com>
Date:   Sun Mar 1 00:38:00 2026 -0500

    initial

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..57b8460
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,9 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.log
+.venv/
+.git/
+.gitignore
+data/
diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..5db2a9f
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,4 @@
+TELEGRAM_BOT_TOKEN=123456:ABCDEF_your_bot_token
+TELEGRAM_CHAT_ID=123456789
+CHECK_INTERVAL_SECONDS=1800
+LOG_LEVEL=INFO
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..f8a9361
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,15 @@
+FROM python:3.12-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY watcher.py ./
+
+VOLUME ["/data"]
+
+CMD ["python", "/app/watcher.py"]
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..815fc61
--- /dev/null
+++ b/README.md
@@ -0,0 +1,62 @@
+# truenas-catalog-notify
+
+Lightweight TrueNAS Apps catalog watcher that sends Telegram alerts when the catalog changes.
+
+## What it tracks
+
+The watcher pulls `https://apps.truenas.com/catalog` over plain HTTP (no browser/emulation), parses app cards, and compares these fields against a saved snapshot:
+
+- app name
+- app URL
+- train
+- added date
+- summary text
+
+On changes, it sends Telegram messages with:
+
+- added apps (`+`)
+- removed apps (`-`)
+- updated apps (`~`) and field-level diffs
+
+## Environment variables
+
+- `TELEGRAM_BOT_TOKEN` (required for notifications)
+- `TELEGRAM_CHAT_ID` (required for notifications)
+- `CHECK_INTERVAL_SECONDS` (default: `1800`)
+- `STATE_PATH` (default: `/data/catalog_state.json`)
+- `CATALOG_URL` (default: `https://apps.truenas.com/catalog`)
+- `REQUEST_TIMEOUT_SECONDS` (default: `30`)
+- `LOG_LEVEL` (default: `INFO`)
+
+## Build
+
+```bash
+docker build -t truenas-catalog-notify .
+```
+
+## Run
+
+```bash
+docker run -d \
+  --name truenas-catalog-notify \
+  -e TELEGRAM_BOT_TOKEN=123456:ABC... \
+  -e TELEGRAM_CHAT_ID=123456789 \
+  -e CHECK_INTERVAL_SECONDS=1800 \
+  -v truenas-catalog-notify-data:/data \
+  --restart unless-stopped \
+  truenas-catalog-notify
+```
+
+## Notes
+
+- First run only stores the initial snapshot (no notification).
+- Notifications start when a later check differs from the saved snapshot.
+- If Telegram variables are missing, the watcher logs changes but skips sending messages.
+- If you hit permissions on `/data/catalog_state.json`, rebuild and recreate the container with the latest image.
+
+## Rebuild after changes
+
+```bash
+docker compose build --no-cache
+docker compose up -d --force-recreate
+```
diff --git a/__pycache__/watcher.cpython-312.pyc b/__pycache__/watcher.cpython-312.pyc
new file mode 100644
index 0000000..21e1620
Binary files /dev/null and b/__pycache__/watcher.cpython-312.pyc differ
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..f215693
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,15 @@
+services:
+  truenas-catalog-notify:
+    build: .
+    container_name: truenas-catalog-notify
+    restart: unless-stopped
+    environment:
+      TELEGRAM_BOT_TOKEN: ${TELEGRAM_BOT_TOKEN}
+      TELEGRAM_CHAT_ID: ${TELEGRAM_CHAT_ID}
+      CHECK_INTERVAL_SECONDS: ${CHECK_INTERVAL_SECONDS:-1800}
+      LOG_LEVEL: ${LOG_LEVEL:-INFO}
+    volumes:
+      - truenas-catalog-notify-data:/data
+
+volumes:
+  truenas-catalog-notify-data:
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..bf4dcfc
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+beautifulsoup4==4.12.3
+requests==2.32.3
diff --git a/watcher.py b/watcher.py
new file mode 100644
index 0000000..7cad0ff
--- /dev/null
+++ b/watcher.py
@@ -0,0 +1,326 @@
+import hashlib
+import json
+import logging
+import os
+import sys
+import time
+from dataclasses import dataclass, asdict
+from datetime import datetime, timezone
+from typing import Dict, List, Tuple
+from urllib.parse import urljoin, urlparse
+
+import requests
+from bs4 import BeautifulSoup
+
+CATALOG_URL = os.getenv("CATALOG_URL", "https://apps.truenas.com/catalog")
+STATE_PATH = os.getenv("STATE_PATH", "/data/catalog_state.json")
+CHECK_INTERVAL_SECONDS = int(os.getenv("CHECK_INTERVAL_SECONDS", "1800"))
+TELEGRAM_BOT_TOKEN = os.getenv("TELEGRAM_BOT_TOKEN", "")
+TELEGRAM_CHAT_ID = os.getenv("TELEGRAM_CHAT_ID", "")
+REQUEST_TIMEOUT_SECONDS = int(os.getenv("REQUEST_TIMEOUT_SECONDS", "30"))
+USER_AGENT = os.getenv(
+    "USER_AGENT",
+    "truenas-catalog-notify/1.0 (+https://apps.truenas.com/catalog)",
+)
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO").upper()
+MAX_MESSAGE_LEN = 3900
+
+
+@dataclass
+class AppSnapshot:
+    name: str
+    url: str
+    train: str
+    added: str
+    summary: str
+    content_hash: str
+
+
+def configure_logging() -> None:
+    logging.basicConfig(
+        level=getattr(logging, LOG_LEVEL, logging.INFO),
+        format="%(asctime)s %(levelname)s %(message)s",
+    )
+
+
+def normalize_text(value: str) -> str:
+    return " ".join(value.split())
+
+
+def compute_hash(parts: List[str]) -> str:
+    digest = hashlib.sha256("||".join(parts).encode("utf-8")).hexdigest()
+    return digest
+
+
+def fetch_catalog_html(session: requests.Session) -> str:
+    response = session.get(
+        CATALOG_URL,
+        timeout=REQUEST_TIMEOUT_SECONDS,
+        headers={"User-Agent": USER_AGENT},
+    )
+    response.raise_for_status()
+    return response.text
+
+
+def is_catalog_app_link(href: str) -> bool:
+    if not href:
+        return False
+    parsed = urlparse(href)
+    path = parsed.path.rstrip("/")
+    return path.startswith("/catalog/") and path != "/catalog"
+
+
+def parse_catalog(html: str) -> Dict[str, AppSnapshot]:
+    soup = BeautifulSoup(html, "html.parser")
+    cards_root = soup.find(id="catalog-cards")
+    candidates = cards_root.find_all("a", href=True) if cards_root else soup.find_all("a", href=True)
+
+    snapshots: Dict[str, AppSnapshot] = {}
+    for anchor in candidates:
+        raw_href = anchor.get("href", "")
+        full_url = urljoin(CATALOG_URL, raw_href)
+        if not is_catalog_app_link(urlparse(full_url).path):
+            continue
+
+        text = normalize_text(anchor.get_text(" ", strip=True))
+        if not text:
+            continue
+
+        name = text.split(" Train:")[0].strip()
+        train = ""
+        added = ""
+        summary = ""
+
+        if " Train:" in text:
+            remainder = text.split(" Train:", 1)[1].strip()
+            if " Added:" in remainder:
+                train_part, after_added = remainder.split(" Added:", 1)
+                train = train_part.strip()
+                pieces = after_added.split(" ", 1)
+                added = pieces[0].strip()
+                summary = pieces[1].strip() if len(pieces) > 1 else ""
+            else:
+                train = remainder
+        else:
+            summary = text
+
+        app_hash = compute_hash([name, train, added, summary, full_url])
+        snapshots[full_url] = AppSnapshot(
+            name=name,
+            url=full_url,
+            train=train,
+            added=added,
+            summary=summary,
+            content_hash=app_hash,
+        )
+
+    return snapshots
+
+
+def load_state(path: str) -> Dict[str, AppSnapshot]:
+    if not os.path.exists(path):
+        return {}
+
+    with open(path, "r", encoding="utf-8") as handle:
+        data = json.load(handle)
+
+    apps = data.get("apps", {})
+    loaded: Dict[str, AppSnapshot] = {}
+    for url, value in apps.items():
+        loaded[url] = AppSnapshot(
+            name=value.get("name", ""),
+            url=value.get("url", url),
+            train=value.get("train", ""),
+            added=value.get("added", ""),
+            summary=value.get("summary", ""),
+            content_hash=value.get("content_hash", ""),
+        )
+    return loaded
+
+
+def save_state(path: str, apps: Dict[str, AppSnapshot]) -> None:
+    directory = os.path.dirname(path)
+    if directory:
+        os.makedirs(directory, exist_ok=True)
+    payload = {
+        "updated_at": datetime.now(timezone.utc).isoformat(),
+        "apps": {url: asdict(snapshot) for url, snapshot in sorted(apps.items())},
+    }
+    with open(path, "w", encoding="utf-8") as handle:
+        json.dump(payload, handle, indent=2, ensure_ascii=False)
+
+
+def format_field_change(label: str, old: str, new: str) -> str:
+    old_clean = old if old else "(empty)"
+    new_clean = new if new else "(empty)"
+    return f"{label}: '{old_clean}' -> '{new_clean}'"
+
+
+def build_diff_message(
+    previous: Dict[str, AppSnapshot],
+    current: Dict[str, AppSnapshot],
+) -> Tuple[str, List[str], int]:
+    prev_urls = set(previous.keys())
+    curr_urls = set(current.keys())
+
+    added_urls = sorted(curr_urls - prev_urls)
+    removed_urls = sorted(prev_urls - curr_urls)
+    common_urls = sorted(curr_urls & prev_urls)
+
+    changed_lines: List[str] = []
+    updated_count = 0
+    for url in common_urls:
+        old = previous[url]
+        new = current[url]
+        if old.content_hash == new.content_hash:
+            continue
+        updated_count += 1
+
+        details: List[str] = []
+        if old.name != new.name:
+            details.append(format_field_change("name", old.name, new.name))
+        if old.train != new.train:
+            details.append(format_field_change("train", old.train, new.train))
+        if old.added != new.added:
+            details.append(format_field_change("added", old.added, new.added))
+        if old.summary != new.summary:
+            details.append(format_field_change("summary", old.summary, new.summary))
+
+        if not details:
+            details.append("metadata changed")
+
+        changed_lines.append(f"~ {new.name} ({new.url})")
+        for detail in details:
+            changed_lines.append(f"  - {detail}")
+
+    header = (
+        f"TrueNAS catalog changed at {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M:%S UTC')}\n"
+        f"Added: {len(added_urls)} | Removed: {len(removed_urls)} | Updated: {updated_count}"
+    )
+
+    lines: List[str] = []
+    for url in added_urls:
+        app = current[url]
+        lines.append(f"+ {app.name} ({app.url})")
+
+    for url in removed_urls:
+        app = previous[url]
+        lines.append(f"- {app.name} ({app.url})")
+
+    lines.extend(changed_lines)
+    return header, lines, updated_count
+
+
+def split_message(header: str, lines: List[str], max_len: int = MAX_MESSAGE_LEN) -> List[str]:
+    if not lines:
+        return [header]
+
+    chunks: List[str] = []
+    current_chunk = header
+
+    for line in lines:
+        candidate = f"{current_chunk}\n{line}"
+        if len(candidate) <= max_len:
+            current_chunk = candidate
+            continue
+
+        chunks.append(current_chunk)
+        current_chunk = f"{header}\n{line}"
+
+    chunks.append(current_chunk)
+    return chunks
+
+
+def send_telegram_message(session: requests.Session, text: str) -> None:
+    if not TELEGRAM_BOT_TOKEN or not TELEGRAM_CHAT_ID:
+        logging.warning("Telegram token/chat id missing; skipping message")
+        return
+
+    endpoint = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
+    payload = {
+        "chat_id": TELEGRAM_CHAT_ID,
+        "text": text,
+        "disable_web_page_preview": True,
+    }
+
+    response = session.post(endpoint, json=payload, timeout=REQUEST_TIMEOUT_SECONDS)
+    response.raise_for_status()
+
+
+def send_startup_notification(session: requests.Session) -> None:
+    message = (
+        "TrueNAS catalog watcher is running ✅\n"
+        f"Started: {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M:%S UTC')}\n"
+        f"Catalog: {CATALOG_URL}\n"
+        f"Interval: {CHECK_INTERVAL_SECONDS}s"
+    )
+    try:
+        send_telegram_message(session, message)
+    except requests.RequestException as exc:
+        logging.error("Failed to send startup Telegram message: %s", exc)
+
+
+def run_once(session: requests.Session, first_run: bool) -> bool:
+    previous_state = load_state(STATE_PATH)
+    html = fetch_catalog_html(session)
+    current_state = parse_catalog(html)
+
+    if not current_state:
+        raise RuntimeError("Parsed zero catalog entries; aborting to avoid overwriting state")
+
+    if first_run and not previous_state:
+        save_state(STATE_PATH, current_state)
+        logging.info("Initial snapshot saved with %d apps", len(current_state))
+        return False
+
+    header, diff_lines, _ = build_diff_message(previous_state, current_state)
+    changed = bool(diff_lines)
+
+    if changed:
+        logging.info("Catalog change detected with %d line items", len(diff_lines))
+        for message in split_message(header, diff_lines):
+            send_telegram_message(session, message)
+    else:
+        logging.info("No catalog changes detected")
+
+    save_state(STATE_PATH, current_state)
+    return changed
+
+
+def validate_env() -> None:
+    if CHECK_INTERVAL_SECONDS < 30:
+        raise ValueError("CHECK_INTERVAL_SECONDS must be >= 30")
+
+
+def main() -> int:
+    configure_logging()
+
+    try:
+        validate_env()
+    except Exception as exc:
+        logging.error("Invalid environment: %s", exc)
+        return 2
+
+    logging.info("Starting TrueNAS catalog watcher")
+    logging.info("Catalog URL: %s", CATALOG_URL)
+    logging.info("State file: %s", STATE_PATH)
+    logging.info("Interval: %ss", CHECK_INTERVAL_SECONDS)
+
+    session = requests.Session()
+    send_startup_notification(session)
+    first_loop = True
+
+    while True:
+        try:
+            run_once(session, first_loop)
+        except requests.RequestException as exc:
+            logging.error("Network error: %s", exc)
+        except Exception as exc:
+            logging.exception("Watcher iteration failed: %s", exc)
+
+        first_loop = False
+        time.sleep(CHECK_INTERVAL_SECONDS)
+
+
+if __name__ == "__main__":
+    sys.exit(main())