services:
  mediacrawler:
    build: .
    image: mediacrawler:latest
    container_name: mediacrawler
    restart: unless-stopped

    # Run as the user that owns this checkout. Without it the container is root,
    # and every file it writes into the mounted tree -- the crawler's per-run
    # jsonl output above all -- comes out root-owned. That does not break the app,
    # but it does lock the operator out of moving or deleting their own
    # deployment, which is exactly what happened the first time this was deployed.
    user: "1000:1000"

    # host networking is a requirement, not a convenience: the crawler attaches
    # to the operator's Chrome at 127.0.0.1:9222, and inside a bridge network
    # that loopback is the container's own, where no browser is listening.
    # It also puts the app port directly on the host, so `ports:` is not used.
    network_mode: host

    env_file:
      - .env
    environment:
      MC_HOST: 0.0.0.0
      MC_PORT: "18051"
      TZ: Asia/Shanghai

    volumes:
      # The code is mounted rather than baked in, so shipping a change is
      # "git pull, restart" instead of an image rebuild. Only the dependencies
      # live in the image, because those are the expensive part and they change
      # rarely -- rebuild only when requirements.txt or the Dockerfile changes.
      - ./:/app