# Usage: # docker compose run archivebox init --setup # docker compose up # 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 MEDIA_MAX_SIZE=750m # docker compose run archivebox help # Documentation: # https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose version: '3.9' services: archivebox: image: ${DOCKER_IMAGE:-archivebox/archivebox:dev} command: server --quick-init 0.0.0.0:8000 ports: - 8000:8000 volumes: - ./data:/data # - ./etc/crontabs:/var/spool/cron/crontabs # uncomment this and archivebox_scheduler below to set up automatic recurring archive jobs # - ./archivebox:/app/archivebox # uncomment this to mount the ArchiveBox source code at runtime (for developers working on archivebox) # build: . # uncomment this to build the image from source code at buildtime (for developers working on archivebox) # dns: # uncomment this and pihole container below for ad-blocking during archiving # - pihole environment: - ALLOWED_HOSTS=* # restrict this to only accept incoming traffic via specific domain name # - 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 # - 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 # - PUID=1000 # set to your host user's UID & GID if you encounter permissions issues # - PGID=1000 # - SEARCH_BACKEND_ENGINE=sonic # uncomment these and sonic container below for better full-text search # - SEARCH_BACKEND_HOST_NAME=sonic # - SEARCH_BACKEND_PASSWORD=SomeSecretPassword # ... # 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) ######## Optional Addons: tweak examples below as needed for your specific use case ######## ### Example: To run the Sonic full-text search backend, first download the config file to sonic.cfg # $ curl -O https://raw.githubusercontent.com/ArchiveBox/ArchiveBox/master/etc/sonic.cfg # After starting, backfill any existing Snapshots into the full-text index: # $ docker-compose run archivebox update --index-only # sonic: # image: valeriansaliou/sonic:latest # expose: # - 1491 # environment: # - SEARCH_BACKEND_PASSWORD=SomeSecretPassword # volumes: # - ./sonic.cfg:/etc/sonic.cfg:ro # - ./data/sonic:/var/lib/sonic/store ### 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: # - 8090:80 # uncomment to access the admin HTTP interface on http://localhost:8090 # environment: # - WEBPASSWORD=SET_THIS_TO_SOME_SECRET_PASSWORD_FOR_ADMIN_DASHBOARD # 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: ${DOCKER_IMAGE:-archivebox/archivebox:dev} # 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 # 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