[App] ArchiveBox (#2393)

* [App] ArchiveBox

* Update apps/archivebox/metadata/description.md

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* feat(docker=compose): add more env vars for app and their default value

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: JigSawFr <JigSawFr@users.noreply.github.com>

apps/archivebox/config.json

@@ -0,0 +1,35 @@
+{
+  "$schema": "../schema.json",
+  "name": "ArchiveBox",
+  "available": true,
+  "exposable": true,
+  "port": 8015,
+  "id": "archivebox",
+  "tipi_version": 1,
+  "version": "0.7.3",
+  "categories": ["media"],
+  "description": "ArchiveBox is a powerful, self-hosted internet archiving solution to collect, save, and view websites offline.",
+  "short_desc": "Open source self-hosted web archiving.",
+  "author": "archivebox",
+  "source": "https://github.com/ArchiveBox/ArchiveBox",
+  "website": "https://archivebox.io",
+  "form_fields": [
+    {
+      "type": "text",
+      "label": "ArchiveBox Username",
+      "max": 50,
+      "min": 3,
+      "required": true,
+      "env_variable": "ARCHIVEBOX_USERNAME"
+    },
+    {
+      "type": "password",
+      "label": "ArchiveBox Password",
+      "max": 50,
+      "min": 12,
+      "required": true,
+      "env_variable": "ARCHIVEBOX_PASSWORD"
+    }
+  ],
+  "supported_architectures": ["arm64", "amd64"]
+}

apps/archivebox/docker-compose.yml

@@ -0,0 +1,54 @@
+services:
+  archivebox:
+    image: archivebox/archivebox:0.7.3
+    restart: unless-stopped
+    container_name: archivebox
+    command: server --quick-init 0.0.0.0:8015
+    environment:
+      - PORT=8015
+      - PUBLIC_INDEX=${ARCHIVEBOX_PUBLIC_INDEX-true} # set to False to prevent anonymous users from viewing snapshot list
+      - PUBLIC_SNAPSHOTS=${ARCHIVEBOX_PUBLIC_SNAPSHOTS-true} # set to False to prevent anonymous users from viewing snapshot content
+      - PUBLIC_ADD_VIEW=${ARCHIVEBOX_PUBLIC_ADD_VIEW-false} # set to True to allow anonymous users to submit new URLs to archive
+      - ADMIN_USERNAME=${ARCHIVEBOX_USERNAME} # create an admin user on first run with the given user/pass combo
+      - ADMIN_PASSWORD=${ARCHIVEBOX_PASSWORD}
+      - PUID=1000 # set to your host user's UID & GID if you encounter permissions issues
+      - PGID=1000
+      - SEARCH_BACKEND_ENGINE=${ARCHIVEBOX_SEARCH_BACKEND_ENGINE} # uncomment these and sonic container below for better full-text search
+      - SEARCH_BACKEND_HOST_NAME=${ARCHIVEBOX_SEARCH_BACKEND_HOST_NAME}
+      - SEARCH_BACKEND_PASSWORD=${ARCHIVEBOX_SEARCH_BACKEND_PASSWORD}
+      - MEDIA_MAX_SIZE=${ARCHIVEBOX_MEDIA_MAX_SIZE-750m} # increase this filesize limit to allow archiving larger audio/video files
+      - TIMEOUT=${ARCHIVEBOX_TIMEOUT-60} # increase this number to 120+ seconds if you see many slow downloads timing out
+      - CHECK_SSL_VALIDITY=${ARCHIVEBOX_CHECK_SSL_VALIDITY-true} # set to False to disable strict SSL checking (allows saving URLs w/ broken certs)
+      - SAVE_ARCHIVE_DOT_ORG=${ARCHIVEBOX_SAVE_ARCHIVE_DOT_ORGE-true} # set to False to disable submitting all URLs to Archive.org when archiving
+    networks:
+      - tipi_main_network
+    ports:
+      - "${APP_PORT}:8015"
+    volumes:
+      - "${APP_DATA_DIR}/data:/data"
+      - "${APP_DATA_DIR}/crontabs:/var/spool/cron/crontabs"
+    labels:
+      # Main
+      traefik.enable: true
+      traefik.http.middlewares.archivebox-web-redirect.redirectscheme.scheme: https
+      traefik.http.services.archivebox.loadbalancer.server.port: 8015
+      # Web
+      traefik.http.routers.archivebox-insecure.rule: Host(`${APP_DOMAIN}`)
+      traefik.http.routers.archivebox-insecure.entrypoints: web
+      traefik.http.routers.archivebox-insecure.service: archivebox
+      traefik.http.routers.archivebox-insecure.middlewares: archivebox-web-redirect
+      # Websecure
+      traefik.http.routers.archivebox.rule: Host(`${APP_DOMAIN}`)
+      traefik.http.routers.archivebox.entrypoints: websecure
+      traefik.http.routers.archivebox.service: archivebox
+      traefik.http.routers.archivebox.tls.certresolver: myresolver
+      # Local domain
+      traefik.http.routers.archivebox-local-insecure.rule: Host(`archivebox.${LOCAL_DOMAIN}`)
+      traefik.http.routers.archivebox-local-insecure.entrypoints: web
+      traefik.http.routers.archivebox-local-insecure.service: archivebox
+      traefik.http.routers.archivebox-local-insecure.middlewares: archivebox-web-redirect
+      # Local domain secure
+      traefik.http.routers.archivebox-local.rule: Host(`archivebox.${LOCAL_DOMAIN}`)
+      traefik.http.routers.archivebox-local.entrypoints: websecure
+      traefik.http.routers.archivebox-local.service: archivebox
+      traefik.http.routers.archivebox-local.tls: true

apps/archivebox/metadata/description.md

@@ -0,0 +1,24 @@
+# ArchiveBox
+
+ArchiveBox is a powerful, self-hosted internet archiving solution to collect, save, and view websites offline.
+
+---
+
+![](https://github.com/ArchiveBox/ArchiveBox/assets/511499/90f1ce3c-75bb-401d-88ed-6297694b76ae?raw=true)
+
+---
+
+Without active preservation effort, everything on the internet eventually disappears or degrades. Archive.org does a great job as a centralized service, but saved URLs have to be public, and they can't save every type of content.
+
+ArchiveBox is an open source tool that lets organizations & individuals archive both public & private web content while retaining control over their data. It can be used to save copies of bookmarks, preserve evidence for legal cases, backup photos from FB/Insta/Flickr or media from YT/Soundcloud/etc., save research papers, and more...
+
+📥 **You can feed ArchiveBox URLs one at a time, or schedule regular imports** from your bookmarks or history, social media feeds or RSS, link-saving services like Pocket/Pinboard, our [Browser Extension](https://chromewebstore.google.com/detail/archivebox-exporter/habonpimjphpdnmcfkaockjnffodikoj), and more.  
+
+**It saves snapshots of the URLs you feed it in several redundant formats.**  
+It also detects any content featured *inside* pages & extracts it out into a folder:
+
+- 🌐 **HTML**/**Any websites** ➡️ `original HTML+CSS+JS`, `singlefile HTML`, `screenshot PNG`, `PDF`, `WARC`, `title`, `article text`, `favicon`, `headers`, ...
+- 🎥 **Social Media**/**News** ➡️ `post content TXT`, `comments`, `title`, `author`, `images`, ...
+- 🎬 **YouTube**/**SoundCloud**/etc. ➡️ `MP3/MP4`s, `subtitles`, `metadata`, `thumbnail`, ...
+- 💾 **Github**/**Gitlab**/etc. links ➡️ `clone of GIT source code`, `README`, `images`, ...
+- ✨ *and more ...