- joplin: self-hosted sync server (PostgreSQL sidecar, APP_BASE_URL from SITE_DOMAIN) - stirling-pdf: PDF toolkit with optional Authelia SSO (no built-in auth) - n8n: workflow automation connecting self-hosted services (WEBHOOK_URL from SITE_DOMAIN) - changedetection: web page change monitoring with playwright-chrome renderer - archivebox: personal Wayback Machine, initializes data dir at install time - calibre-web: ebook library UI with Calibre conversion support (linuxserver image) - homebox: home inventory and asset management All services follow the standalone bootstrap pattern and support local/remote Caddy. README.md updated with new services in appropriate group rows.
286 lines
10 KiB
Bash
286 lines
10 KiB
Bash
#!/bin/bash
|
|
# services/archivebox.sh — Self-hosted web archiving (ArchiveBox).
|
|
# Part of the modular post-install system (sourced by setup.sh).
|
|
#
|
|
# Can also be run standalone on any machine:
|
|
# sudo bash archivebox.sh
|
|
# (Docker must already be installed when run standalone)
|
|
|
|
# ── Standalone bootstrap ──────────────────────────────────────────────────────
|
|
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
|
|
[[ "$(id -u)" == "0" ]] || { echo "Run with sudo: sudo bash $0"; exit 1; }
|
|
|
|
_SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
_COMMON="$_SELF_DIR/../lib/common.sh"
|
|
|
|
if [[ -f "$_COMMON" ]]; then
|
|
source "$_COMMON"
|
|
else
|
|
log_info() { echo -e "\033[0;34m[INFO]\033[0m $*"; }
|
|
log_success() { echo -e "\033[0;32m[OK]\033[0m $*"; }
|
|
log_warning() { echo -e "\033[1;33m[WARN]\033[0m $*"; }
|
|
log_error() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
|
|
|
|
require_docker() {
|
|
command -v docker &>/dev/null || {
|
|
log_error "Docker not found. Install it first:"
|
|
log_error " curl -fsSL https://get.docker.com | sudo sh"
|
|
return 1
|
|
}
|
|
docker compose version &>/dev/null || {
|
|
log_error "Docker Compose plugin missing:"
|
|
log_error " sudo apt-get install -y docker-compose-plugin"
|
|
return 1
|
|
}
|
|
}
|
|
|
|
ensure_docker_dir_ownership() {
|
|
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$@" 2>/dev/null || true
|
|
}
|
|
|
|
prompt_text() {
|
|
local _q="$1" _def="$2" _var="$3" _r
|
|
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
|
|
read -r -p " $_q " _r
|
|
eval "$_var='${_r:-$_def}'"
|
|
}
|
|
|
|
prompt_yn() {
|
|
local _q="$1" _def="$2" _var="$3" _r
|
|
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
|
|
read -r -p " $_q " _r
|
|
eval "$_var='${_r:-$_def}'"
|
|
}
|
|
|
|
configure_caddy_for_service() {
|
|
local _name="$1" _upstream="$2" _subdomain="$3" _extra="${4:-}"
|
|
local _caddy_dir="$DOCKER_DIR/caddy"
|
|
local _caddyfile="$_caddy_dir/Caddyfile"
|
|
local _display_port="${_upstream##*:}"
|
|
|
|
local _mode="none"
|
|
[[ -d "$_caddy_dir" ]] && _mode="local"
|
|
[[ -n "${CADDY_REMOTE_HOST:-}" ]] && [[ "$_mode" != "local" ]] && _mode="remote"
|
|
[[ "$_mode" == "none" ]] && {
|
|
log_info "Access $_name directly on port $_display_port."
|
|
return 0
|
|
}
|
|
|
|
echo ""
|
|
local _do_caddy=""
|
|
if [[ "$_mode" == "remote" ]]; then
|
|
log_info "Remote Caddy configured (${CADDY_REMOTE_HOST})."
|
|
log_info "A snippet file will be saved to ~/docker/caddy-snippets/."
|
|
fi
|
|
read -r -p " Configure Caddy reverse proxy for $_name? [y/N]: " _do_caddy
|
|
[[ "${_do_caddy,,}" == "y" ]] || {
|
|
log_info "Skipping — access at: http://localhost:$_display_port"
|
|
return 0
|
|
}
|
|
|
|
local _default_domain=""
|
|
if [[ -n "${SITE_DOMAIN:-}" ]] && [[ "$SITE_DOMAIN" != "example.com" ]]; then
|
|
_default_domain="${_subdomain}.${SITE_DOMAIN}"
|
|
log_info "Default: $_default_domain"
|
|
fi
|
|
local _domain=""
|
|
read -r -p " Domain [${_default_domain:-required}]: " _domain
|
|
_domain="${_domain:-$_default_domain}"
|
|
[[ -n "$_domain" ]] || { log_warning "No domain entered — skipping Caddy."; return 0; }
|
|
|
|
local _block_upstream="$_upstream"
|
|
if [[ "$_mode" == "remote" ]]; then
|
|
_block_upstream="${CADDY_REMOTE_HOST}:${_display_port}"
|
|
fi
|
|
|
|
local _site_block
|
|
_site_block="$(cat << CBLOCK
|
|
|
|
# $_name
|
|
${_domain} {
|
|
reverse_proxy ${_block_upstream}
|
|
|
|
header {
|
|
Strict-Transport-Security "max-age=31536000; includeSubDomains; preload"
|
|
X-Content-Type-Options "nosniff"
|
|
X-Frame-Options "SAMEORIGIN"
|
|
Referrer-Policy "strict-origin-when-cross-origin"
|
|
}
|
|
|
|
log {
|
|
output file /var/log/caddy/${_domain}.log
|
|
format json
|
|
}
|
|
${_extra}
|
|
}
|
|
CBLOCK
|
|
)"
|
|
|
|
if [[ "$_mode" == "local" ]]; then
|
|
if [[ -f "$_caddyfile" ]]; then
|
|
local _bk="$_caddy_dir/Caddyfile.backup.$(date +%Y%m%d-%H%M%S)"
|
|
cp "$_caddyfile" "$_bk"
|
|
log_info "Backed up Caddyfile to $(basename "$_bk")"
|
|
else
|
|
touch "$_caddyfile"
|
|
fi
|
|
|
|
if grep -q "^${_domain}" "$_caddyfile" 2>/dev/null; then
|
|
log_warning "$_domain already in Caddyfile"
|
|
local _ow=""
|
|
read -r -p " Overwrite? [y/N]: " _ow
|
|
[[ "${_ow,,}" == "y" ]] || { log_info "Keeping existing entry."; return 0; }
|
|
sed -i "/^${_domain}/,/^}/d" "$_caddyfile"
|
|
fi
|
|
|
|
printf '%s\n' "$_site_block" >> "$_caddyfile"
|
|
log_success "Added $_domain to Caddyfile"
|
|
docker exec caddy caddy fmt --overwrite /etc/caddy/Caddyfile 2>/dev/null || true
|
|
if docker exec caddy caddy reload --config /etc/caddy/Caddyfile 2>/dev/null; then
|
|
log_success "$_name accessible at: https://$_domain"
|
|
else
|
|
log_warning "Reload failed — check: docker logs caddy"
|
|
log_info "Manual reload: docker exec caddy caddy reload --config /etc/caddy/Caddyfile"
|
|
fi
|
|
else
|
|
local _snippet_dir="$DOCKER_DIR/caddy-snippets"
|
|
local _snippet_file="$_snippet_dir/${_subdomain}.caddy"
|
|
mkdir -p "$_snippet_dir"
|
|
printf '%s\n' "$_site_block" > "$_snippet_file"
|
|
chown "$ACTUAL_USER:$ACTUAL_USER" "$_snippet_file" 2>/dev/null || true
|
|
log_success "Snippet saved: $_snippet_file"
|
|
log_info "Copy to Caddy machine:"
|
|
log_info " scp $_snippet_file caddy-host:~/caddy-snippets/"
|
|
log_info " rsync -av $_snippet_dir/ caddy-host:~/caddy-snippets/ (all at once)"
|
|
fi
|
|
}
|
|
write_readme() {
|
|
local _dir="$1"; shift
|
|
mkdir -p "$_dir"
|
|
cat > "$_dir/README.md"
|
|
}
|
|
fi
|
|
|
|
ACTUAL_USER="${ACTUAL_USER:-${SUDO_USER:-$USER}}"
|
|
ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "${HOME:-/root}")"
|
|
DOCKER_DIR="${DOCKER_DIR:-$ACTUAL_HOME/docker}"
|
|
DRY_RUN="${DRY_RUN:-false}"
|
|
UNATTENDED="${UNATTENDED:-false}"
|
|
SITE_TZ="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}"
|
|
SITE_DOMAIN="${SITE_DOMAIN:-example.com}"
|
|
SITE_CADDY_NET="${SITE_CADDY_NET:-caddy_net}"
|
|
CADDY_REMOTE_HOST="${CADDY_REMOTE_HOST:-}"
|
|
|
|
register_service() { :; }
|
|
_RUN_STANDALONE=1
|
|
fi
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
register_service archivebox utilities "Self-hosted web archiving — save pages like Wayback Machine (ArchiveBox)" 8000
|
|
|
|
install_archivebox() {
|
|
require_docker || return 1
|
|
|
|
local AB_DIR="$DOCKER_DIR/archivebox"
|
|
|
|
if [ "$DRY_RUN" = true ]; then
|
|
echo "[DRY-RUN] archivebox would:"
|
|
echo " - Create $AB_DIR with docker-compose.yml"
|
|
echo " - Initialize ArchiveBox data directory"
|
|
echo " - Expose port 8000 (web UI)"
|
|
return 0
|
|
fi
|
|
|
|
mkdir -p "$AB_DIR"
|
|
ensure_docker_dir_ownership "$AB_DIR"
|
|
cd "$AB_DIR" || return 1
|
|
|
|
cat > docker-compose.yml << 'ABCOMPOSE'
|
|
name: archivebox
|
|
|
|
services:
|
|
archivebox:
|
|
image: archivebox/archivebox:latest
|
|
container_name: archivebox
|
|
restart: unless-stopped
|
|
user: "1000:1000"
|
|
environment:
|
|
- ALLOWED_HOSTS=*
|
|
- MEDIA_MAX_SIZE=750m
|
|
- PUBLIC_INDEX=True
|
|
- PUBLIC_SNAPSHOTS=True
|
|
- PUBLIC_ADD_VIEW=False
|
|
volumes:
|
|
- ./data:/data
|
|
ports:
|
|
- "8000:8000"
|
|
networks:
|
|
- caddy_net
|
|
|
|
networks:
|
|
caddy_net:
|
|
external: true
|
|
name: ${CADDY_NET:-caddy_net}
|
|
ABCOMPOSE
|
|
|
|
cat > .env << ABENV
|
|
CADDY_NET=$SITE_CADDY_NET
|
|
ABENV
|
|
|
|
mkdir -p data
|
|
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$AB_DIR"
|
|
|
|
log_info "Initializing ArchiveBox data directory..."
|
|
docker compose run --rm archivebox init --setup \
|
|
&& log_success "ArchiveBox initialized" \
|
|
|| log_warning "Init failed — will retry on first start"
|
|
|
|
configure_caddy_for_service "ArchiveBox" "archivebox:8000" "archive"
|
|
|
|
write_readme "$AB_DIR" << 'MD'
|
|
# ArchiveBox
|
|
|
|
Self-hosted web archiving — saves full snapshots of web pages (HTML, screenshots,
|
|
PDFs, WARC) like a personal Wayback Machine.
|
|
|
|
- Web UI: http://localhost:8000
|
|
|
|
## Manage
|
|
```bash
|
|
cd ~/docker/archivebox
|
|
docker compose up -d # start
|
|
docker compose down # stop
|
|
docker compose logs -f # logs
|
|
docker compose pull && docker compose up -d # update
|
|
```
|
|
|
|
## Add URLs to archive
|
|
```bash
|
|
# Via web UI — visit http://localhost:8000 and use the Add page
|
|
# Via CLI:
|
|
echo "https://example.com" | docker compose run --rm archivebox add
|
|
docker compose run --rm archivebox add --depth=1 https://example.com
|
|
```
|
|
|
|
## Create admin user
|
|
```bash
|
|
docker compose run --rm archivebox manage createsuperuser
|
|
```
|
|
MD
|
|
|
|
local START_AB=""
|
|
prompt_yn "Start ArchiveBox now? (y/n):" "y" START_AB
|
|
if [ "$START_AB" = "y" ] || [ "$START_AB" = "Y" ]; then
|
|
docker compose up -d \
|
|
&& log_success "ArchiveBox started — http://localhost:8000" \
|
|
|| log_warning "Start failed — check: docker compose logs"
|
|
fi
|
|
|
|
echo ""
|
|
echo " Web UI: http://localhost:8000"
|
|
echo " Add URLs via the web UI or: echo 'URL' | docker compose run --rm archivebox add"
|
|
echo ""
|
|
}
|
|
|
|
[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_archivebox
|