Best practice to store lager container-data

• ArchiveBox

  248 19,672 9.7 Python

  🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...

  

# 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 PUBLIC_INDEX=True # docker-compose run archivebox help # Documentation: # https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose version: '2.4' services: archivebox: # build: . # for developers working on archivebox image: ${DOCKER_IMAGE:-archivebox/archivebox:master} container_name: archivebox command: server --quick-init 0.0.0.0:8000 ports: - 8000:8000 environment: - TIMEOUT=120 # Seconds - MEDIA_TIMEOUT=3600 # Seconds - ALLOWED_HOSTS=* # add any config options you want as env vars - MEDIA_MAX_SIZE=750m - SEARCH_BACKEND_ENGINE=sonic # uncomment these if you enable sonic below - SEARCH_BACKEND_HOST_NAME=sonic - SEARCH_BACKEND_PASSWORD=MYPW volumes: - /etc/localtime:/etc/localtime:ro - ./data:/data - archivebox-archive:/data/archive # - ./archivebox:/app/archivebox # for developers working on archivebox labels: - "traefik.enable=true" - "traefik.http.routers.archivebox.entrypoints=http" - "traefik.http.routers.archivebox.rule=Host(`myurl.de`)" - "traefik.http.middlewares.archivebox-https-redirect.redirectscheme.scheme=https" - "traefik.http.routers.archivebox.middlewares=archivebox-https-redirect" - "traefik.http.routers.archivebox-secure.entrypoints=https" - "traefik.http.routers.archivebox-secure.rule=Host(`myurl.de`)" - "traefik.http.routers.archivebox-secure.tls=true" - "traefik.http.routers.archivebox.tls.certresolver=cloudflare" - "traefik.http.routers.archivebox-secure.service=archivebox" - "traefik.http.services.archivebox.loadbalancer.server.port=8000" - "traefik.docker.network=proxy" networks: - "internal" - "proxy" depends_on: - sonic # 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 index: docker-compose run archivebox update --index-only sonic: image: valeriansaliou/sonic:v1.3.0 container_name: archivebox-sonic expose: - 1491 environment: - SEARCH_BACKEND_PASSWORD=MYPW volumes: - ./sonic.cfg:/etc/sonic.cfg:ro - ./data/sonic:/var/lib/sonic/store networks: - "internal" volumes: archivebox-archive: driver: local driver_opts: type: "nfs" o: "nfsvers=4,addr=192.168.178.8,rw" device: ":/volume1/docker/archivebox/archive" networks: internal: internal: true proxy: external: true

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project