# Telegram Channel Analyzer Bot

Telegram bot that analyzes public channels using Claude AI. Fetches channel history via Telethon, chunks messages, summarizes with Claude, and delivers a report back in Telegram.

## Report Types

- **Content Analysis** — topics, tone, themes, content strategy
- **Content + Stats** — above + posting frequency, engagement patterns
- **Full Audit** — all above + sentiment, audience insights, recommendations

## Prerequisites

- Telegram Bot token from [@BotFather](https://t.me/BotFather)
- Telegram API credentials from [my.telegram.org](https://my.telegram.org)
- Anthropic API key from [console.anthropic.com](https://console.anthropic.com)
- Docker or Podman

## Setup

```bash
cp .env.example .env
# Edit .env with your credentials
```

`.env` values (no inline comments):
```
BOT_TOKEN=123456:ABC...
TELEGRAM_API_ID=12345678
TELEGRAM_API_HASH=abc123def456...
TELEGRAM_PHONE=+1234567890
ANTHROPIC_API_KEY=sk-ant-...
CLAUDE_MODEL=claude-haiku-4-5
```

Available models: `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-haiku-4-5`

## Run with Docker

```bash
# Build
docker build -f Containerfile -t tg-analyzer .

# First run: interactive login to create Telethon session
docker run -it --env-file .env -v ./data:/app/data tg-analyzer python -m bot --login

# Run the bot
docker run -d --env-file .env -v ./data:/app/data --name tg-analyzer --restart unless-stopped tg-analyzer
```

## Run with Podman

```bash
# Build
podman build -t tg-analyzer .

# First run: interactive login
podman run -it --env-file .env -v ./data:/app/data tg-analyzer python -m bot --login

# Run the bot
podman run -d --env-file .env -v ./data:/app/data --name tg-analyzer tg-analyzer
```

## Run with Compose

```bash
# Login first (see above), then:
podman compose up -d
# or
docker compose up -d
```

## Usage

Send to your bot in Telegram:

```
/analyze @channel_username
```

Select a report type from the inline keyboard. The bot will show progress as it fetches and analyzes.

## Project Structure

```
bot/
├── __main__.py          # Entrypoint: aiogram + Telethon on shared loop
├── config.py            # pydantic-settings from env vars
├── models.py            # ReportType enum, ChannelMessage dataclass
├── handlers/
│   ├── start.py         # /start, /help
│   └── analyze.py       # /analyze + report type selection + progress
├── services/
│   ├── fetcher.py       # Telethon: read channel history
│   ├── chunker.py       # Token-bounded message chunking
│   ├── analyzer.py      # Claude API: chunk summaries → synthesis
│   └── formatter.py     # Split report into Telegram-safe HTML messages
└── prompts/
    ├── chunk_summary.py # Per-chunk extraction prompts
    └── synthesis.py     # Final synthesis prompts
```

## Rate Limits

The bot respects Anthropic API rate limits with automatic retry and cooldown between chunks. On the free/low tier (30K input tokens/min), a large channel may take several minutes.