archival.ArchiveBox/docker-compose.yml

# Usage:
#     docker-compose up -d
#     docker-compose run archivebox init
#     echo "https://example.com" | docker-compose run archivebox archivebox add
#     docker-compose run archivebox add --depth=1 https://example.com/some/feed.rss
#     docker-compose run archivebox config --set PUBLIC_INDEX=True
# Documentation:
#     https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose

version: '3.7'

services:
    archivebox:
        # build: .
        image: ${DOCKER_IMAGE:-archivebox/archivebox:latest} 
        command: server 0.0.0.0:8000
        stdin_open: true
        tty: true
        ports:
            - 8000:8000
        environment:
            - USE_COLOR=True
            - SHOW_PROGRESS=False
            - SEARCH_BACKEND_ENGINE=sonic
            - SEARCH_BACKEND_HOST_NAME=sonic
            - SEARCH_BACKEND_PASSWORD=SecretPassword
        volumes:
            - ./data:/data
        depends_on:
            - sonic
    
    # Run sonic search backend
    sonic:
        image: valeriansaliou/sonic:v1.3.0    
        ports:
            - 1491:1491
        environment:
            - SEARCH_BACKEND_PASSWORD=SecretPassword
        volumes:
            - ./etc/sonic/config.cfg:/etc/sonic.cfg
            - ./data:/var/lib/sonic/store/

    # Optional Addons: tweak these examples as needed for your specific use case

    # Example: Run scheduled imports in a docker instead of using cron on the
    # host machine, add tasks and see more info with archivebox schedule --help
    # scheduler:
    #    image: archivebox/archivebox:latest
    #    command: schedule --foreground --every=day --depth=1 'https://getpocket.com/users/USERNAME/feed/all'
    #    environment:
    #        - USE_COLOR=True
    #        - SHOW_PROGRESS=False
    #    volumes:
    #        - ./data:/data
    
    # Example: Put Nginx in front of the ArchiveBox server for SSL termination
    # nginx:
    #     image: nginx:alpine
    #     ports:
    #         - 443:443
    #         - 80:80
    #     volumes:
    #         - ./etc/nginx/nginx.conf:/etc/nginx/nginx.conf
    #         - ./data:/var/www

    # Example: run all your ArchiveBox traffic through a WireGuard VPN tunnel
    # wireguard:
    #   image: linuxserver/wireguard
    #   network_mode: 'service:archivebox'
    #   cap_add:
    #     - NET_ADMIN
    #     - SYS_MODULE
    #   sysctls:
    #     - net.ipv4.conf.all.rp_filter=2
    #     - net.ipv4.conf.all.src_valid_mark=1
    #   volumes:
    #     - /lib/modules:/lib/modules
    #     - ./wireguard.conf:/config/wg0.conf:ro
    
    # Example: Run PYWB in parallel and auto-import WARCs from ArchiveBox
    # pywb:
    #     image: webrecorder/pywb:latest
    #     entrypoint: /bin/sh 'wb-manager add default /archivebox/archive/*/warc/*.warc.gz; wayback --proxy;'
    #     environment:
    #         - INIT_COLLECTION=archivebox
    #     ports:
    #         - 8080:8080
    #     volumes:
    #         ./data:/archivebox
    #         ./data/wayback:/webarchive