ArchiveBox/docker-compose.yml

# Usage:
#     docker compose up
#     echo 'https://example.com' | docker compose run -T archivebox add
#     docker compose run archivebox add --depth=1 'https://news.ycombinator.com'
#     docker compose run archivebox config --set SAVE_ARCHIVE_DOT_ORG=False
#     docker compose run archivebox help
# Documentation:
#     https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose

services:
    archivebox:
        image: archivebox/archivebox:latest
        ports:
            - 8000:8000
        volumes:
            - ./data:/data
        environment:
            # - ADMIN_USERNAME=admin            # create an admin user on first run with the given user/pass combo
            # - ADMIN_PASSWORD=SomeSecretPassword
            - ALLOWED_HOSTS=*                   # restrict this to only accept incoming traffic via specific domain name
            - PUBLIC_INDEX=True                 # set to False to prevent anonymous users from viewing snapshot list
            - PUBLIC_SNAPSHOTS=True             # set to False to prevent anonymous users from viewing snapshot content
            - PUBLIC_ADD_VIEW=False             # set to True to allow anonymous users to submit new URLs to archive
            - SEARCH_BACKEND_ENGINE=sonic       # tells ArchiveBox to use sonic container below for fast full-text search
            - SEARCH_BACKEND_HOST_NAME=sonic
            - SEARCH_BACKEND_PASSWORD=SomeSecretPassword
            # - PUID=911                        # set to your host user's UID & GID if you encounter permissions issues
            # - PGID=911                        # UID/GIDs <500 may clash with existing users and are not recommended
            # - MEDIA_MAX_SIZE=750m             # increase this filesize limit to allow archiving larger audio/video files
            # - TIMEOUT=60                      # increase this number to 120+ seconds if you see many slow downloads timing out
            # - CHECK_SSL_VALIDITY=True         # set to False to disable strict SSL checking (allows saving URLs w/ broken certs)
            # - SAVE_ARCHIVE_DOT_ORG=True       # set to False to disable submitting all URLs to Archive.org when archiving
            # ...
            # add further configuration options from archivebox/config.py as needed (to apply them only to this container)
            # or set using `docker compose run archivebox config --set SOME_KEY=someval` (to persist config across all containers)
        # For ad-blocking during archiving, uncomment this section and pihole service section below
        # networks:
        #   - dns
        # dns:
        #   - 172.20.0.53


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

    ### This optional container runs any scheduled tasks in the background, add new tasks like so:
    #   $ docker compose run archivebox schedule --add --every=day --depth=1 'https://example.com/some/rss/feed.xml'
    # then restart the scheduler container to apply any changes to the scheduled task list:
    #   $ docker compose restart archivebox_scheduler

    archivebox_scheduler:
       image: archivebox/archivebox:latest
       command: schedule --foreground --update --every=day
       environment:
           - TIMEOUT=120                       # use a higher timeout than the main container to give slow tasks more time when retrying
           # - PUID=502                        # set to your host user's UID & GID if you encounter permissions issues
           # - PGID=20
       volumes:
           - ./data:/data
       # cpus: 2                               # uncomment / edit these values to limit scheduler container resource consumption
       # mem_limit: 2048m
       # restart: always


    ### This runs the optional Sonic full-text search backend (much faster than default rg backend).
    # If Sonic is ever started after not running for a while, update its full-text index by running:
    #   $ docker-compose run archivebox update --index-only

    sonic:
        image: valeriansaliou/sonic:latest
        build:
            # custom build just auto-downloads archivebox's default sonic.cfg as a convenience
            # not needed after first run / if you have already have ./etc/sonic.cfg present
            dockerfile_inline: |
                FROM quay.io/curl/curl:latest AS config_downloader
                RUN curl -fsSL 'https://raw.githubusercontent.com/ArchiveBox/ArchiveBox/main/etc/sonic.cfg' > /tmp/sonic.cfg
                FROM valeriansaliou/sonic:latest
                COPY --from=config_downloader /tmp/sonic.cfg /etc/sonic.cfg                
        expose:
            - 1491
        environment:
            - SEARCH_BACKEND_PASSWORD=SomeSecretPassword
        volumes:
            - ./sonic.cfg:/etc/sonic.cfg
            - ./data/sonic:/var/lib/sonic/store


    ### This container runs xvfb+noVNC so you can watch the ArchiveBox browser as it archives things,
    # or remote control it to set up a chrome profile w/ login credentials for sites you want to archive.
    # https://github.com/ArchiveBox/ArchiveBox/wiki/Chromium-Install#setting-up-a-chromium-user-profile

    novnc:
        image: theasp/novnc:latest
        environment:
            - DISPLAY_WIDTH=1920
            - DISPLAY_HEIGHT=1080
            - RUN_XTERM=no
        ports:
            # to view/control ArchiveBox's browser, visit: http://127.0.0.1:8080/vnc.html
            # restricted to access from localhost by default because it has no authentication
            - 127.0.0.1:8080:8080

    
    ### Example: Put Nginx in front of the ArchiveBox server for SSL termination and static file serving.
    # You can also any other ingress provider for SSL like Apache, Caddy, Traefik, Cloudflare Tunnels, etc.

    # nginx:
    #     image: nginx:alpine
    #     ports:
    #         - 443:443
    #         - 80:80
    #     volumes:
    #         - ./etc/nginx.conf:/etc/nginx/nginx.conf
    #         - ./data:/var/www


    ### Example: To run pihole in order to block ad/tracker requests during archiving,
    # uncomment this block and set up pihole using its admin interface

    # pihole:
    #   image: pihole/pihole:latest
    #   ports:
    #     # access the admin HTTP interface on http://localhost:8090
    #     - 127.0.0.1:8090:80
    #   environment:
    #     - WEBPASSWORD=SET_THIS_TO_SOME_SECRET_PASSWORD_FOR_ADMIN_DASHBOARD
    #     - DNSMASQ_LISTENING=all
    #   dns:
    #     - 127.0.0.1
    #     - 1.1.1.1
    #   networks:
    #     dns:
    #       ipv4_address: 172.20.0.53
    #   volumes:
    #     - ./etc/pihole:/etc/pihole
    #     - ./etc/dnsmasq:/etc/dnsmasq.d


    ### Example: Enable ability to run regularly scheduled archiving tasks by uncommenting this container
    #   $ docker compose run archivebox schedule --every=day --depth=1 'https://example.com/some/rss/feed.xml'
    # then restart the scheduler container to apply the changes to the schedule
    #   $ docker compose restart archivebox_scheduler

    # archivebox_scheduler:
    #    image: archivebox/archivebox:latest
    #    command: schedule --foreground
    #    environment:
    #        - MEDIA_MAX_SIZE=750m               # increase this number to allow archiving larger audio/video files
    #        # - TIMEOUT=60                      # increase if you see timeouts often during archiving / on slow networks
    #        # - ONLY_NEW=True                   # set to False to retry previously failed URLs when re-adding instead of skipping them
    #        # - CHECK_SSL_VALIDITY=True         # set to False to allow saving URLs w/ broken SSL certs
    #        # - SAVE_ARCHIVE_DOT_ORG=True       # set to False to disable submitting URLs to Archive.org when archiving
    #        # - PUID=502                        # set to your host user's UID & GID if you encounter permissions issues
    #        # - PGID=20
    #    volumes:
    #        - ./data:/data
    #        - ./etc/crontabs:/var/spool/cron/crontabs
    #    # cpus: 2                               # uncomment / edit these values to limit container resource consumption
    #    # mem_limit: 2048m
    #    # shm_size: 1024m


    ### Example: Put Nginx in front of the ArchiveBox server for SSL termination

    # nginx:
    #     image: nginx:alpine
    #     ports:
    #         - 443:443
    #         - 80:80
    #     volumes:
    #         - ./etc/nginx.conf:/etc/nginx/nginx.conf
    #         - ./data:/var/www


    ### Example: run all your ArchiveBox traffic through a WireGuard VPN tunnel to avoid IP blocks.
    # You can also use any other VPN that works at the docker IP level, e.g. Tailscale, OpenVPN, etc.
    
    # wireguard:
    #   image: linuxserver/wireguard:latest
    #   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 -c '(wb-manager init default || test $$? -eq 2) && wb-manager add default /archivebox/archive/*/warc/*.warc.gz; wayback;'
    #     environment:
    #         - INIT_COLLECTION=archivebox
    #     ports:
    #         - 8080:8080
    #     volumes:
    #         - ./data:/archivebox
    #         - ./data/wayback:/webarchive


networks:
    # network just used for pihole container to offer :53 dns resolving on fixed ip for archivebox container
    dns:
        ipam:
            driver: default
            config:
                - subnet: 172.20.0.0/24


# To use remote storage for your ./data/archive (e.g. Amazon S3, Backblaze B2, Google Drive, OneDrive, SFTP, etc.)
#   Follow the steps here to set up the Docker RClone Plugin https://rclone.org/docker/
#     $ docker plugin install rclone/docker-volume-rclone:amd64 --grant-all-permissions --alias rclone
#     $ nano /var/lib/docker-plugins/rclone/config/rclone.conf
#     [examplegdrive]
#     type = drive
#     scope = drive
#     drive_id = 1234567...
#     root_folder_id = 0Abcd...
#     token = {"access_token":...}

# volumes:
#     archive:
#         driver: rclone
#         driver_opts:
#             remote: 'examplegdrive:archivebox'
#             allow_other: 'true'
#             vfs_cache_mode: full
#             poll_interval: 0