mangaBookmark/chrome/entrypoint.sh

#!/bin/sh
set -eu

# A UTC clock is itself the bot signal — Cloudflare treats it as the datacenter
# default — and kagane's challenge then never clears. Measured 2026-08-08 with
# an identical container on one Indonesian egress IP: UTC never cleared in 60s
# (twice), while Asia/Jakarta and America/New_York both cleared in 4s. Any real
# zone will do; the zone does not have to match the IP's country, it just must
# not be UTC. It does have to be right the way Chrome reads it.
#
# TZ must carry the zone *name*. Chrome resolves the zone through ICU, which
# takes the name from /etc/localtime's symlink target and ignores the file's
# contents; bind-mounting the host's /etc/localtime therefore lands on the
# image's own symlink to Etc/UTC and leaves glibc reporting +07 while Chrome
# still reports UTC. /etc/timezone, mounted by docker-compose.yml, is the name.
[ -n "${TZ:-}" ] || TZ=$(cat /etc/timezone 2>/dev/null || echo UTC)
export TZ

state=/home/chrome/state
profile=/home/chrome/profile
lock_file=$state/lock
pid_file=$state/chrome.pid
connections_dir=$state/connections
last_use_file=$state/last-use
idle_seconds=300

mkdir -p "$state" "$profile" "$connections_dir"
exec 9>>"$lock_file"

# Chrome's own UA advertises "HeadlessChrome" under --headless=new, and that
# one token is the difference between kagane.to's challenge clearing in ~4s and
# never clearing at all. Read the installed major version so client hints and
# the UA stay aligned after an image rebuild.
major=$(google-chrome-stable --version | sed -E 's/[^0-9]*([0-9]+)\..*/\1/')
ua="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/${major}.0.0.0 Safari/537.36"

lock() {
	flock 9
}

unlock() {
	flock -u 9
}

browser_alive() {
	[ -s "$pid_file" ] || return 1
	pid=$(cat "$pid_file")
	[ -n "$pid" ] && kill -0 "$pid" 2>/dev/null
}

has_connections() {
	for marker in "$connections_dir"/*; do
		[ -e "$marker" ] || continue
		pid=${marker##*/}
		if kill -0 "$pid" 2>/dev/null; then
			return 0
		fi
		# A SIGKILLed helper cannot run its cleanup trap. Reconcile its marker
		# here so one dead client cannot pin Chrome forever.
		rm -f "$marker"
	done
	return 1
}

start_browser() {
	# No --enable-automation: it sets navigator.webdriver, the first thing a
	# bot check reads. setsid gives Chrome a process group so the reaper can
	# terminate its renderer children with the browser.
	# --no-sandbox avoids granting SYS_ADMIN solely for Docker's unavailable
	# user namespaces; containment is the unprivileged user and private network.
	setsid google-chrome-stable \
		--headless=new \
		--no-sandbox \
		--remote-debugging-port=9223 \
		--user-agent="$ua" \
		--user-data-dir="$profile" \
		--no-first-run \
		--no-default-browser-check \
		--disable-gpu \
		about:blank >/dev/null 2>&1 &
	printf '%s\n' "$!" >"$pid_file"
}

stop_browser() {
	pid=$(cat "$pid_file")
	kill -TERM -- "-$pid" 2>/dev/null || kill -TERM "$pid" 2>/dev/null || true
	i=0
	while kill -0 "$pid" 2>/dev/null && [ "$i" -lt 100 ]; do
		i=$((i + 1))
		sleep 0.1
	done
	if kill -0 "$pid" 2>/dev/null; then
		kill -KILL -- "-$pid" 2>/dev/null || kill -KILL "$pid" 2>/dev/null || true
	fi
	rm -f "$pid_file"
}

wait_for_browser() {
	i=0
	while [ "$i" -lt 300 ]; do
		if wget -qO /dev/null http://127.0.0.1:9223/json/version; then
			return 0
		fi
		browser_alive || return 1
		i=$((i + 1))
		sleep 0.1
	done
	return 1
}

finish_connection() {
	lock
	rm -f "$connection_marker"
	date +%s >"$last_use_file"
	unlock
}

connection_signal() {
	trap - INT TERM HUP
	finish_connection
	exit 143
}

connection() {
	connection_marker=$connections_dir/$$
	lock
	: >"$connection_marker"
	if ! browser_alive; then
		rm -f "$pid_file"
		start_browser
	fi
	date +%s >"$last_use_file"
	unlock

	trap connection_signal INT TERM HUP
	if wait_for_browser; then
		if socat STDIO TCP:127.0.0.1:9223; then
			result=0
		else
			result=$?
		fi
	else
		result=1
	fi
	finish_connection
	return "$result"
}

reaper() {
	while :; do
		sleep 10
		lock
		if ! has_connections && browser_alive; then
			now=$(date +%s)
			last=$(cat "$last_use_file" 2>/dev/null || printf '%s' "$now")
			if [ $((now - last)) -ge "$idle_seconds" ]; then
				stop_browser
			fi
		fi
		unlock
	done
}

if [ "${1:-}" = connection ]; then
	connection
	exit $?
fi

# The files are process state, not the Chrome profile. The profile is a named
# volume in Compose, so clearance survives both a reap and a container rebuild.
for marker in "$connections_dir"/*; do
	[ -e "$marker" ] || continue
	rm -f "$marker"
done
rm -f "$pid_file" "$last_use_file"

# Chrome binds DevTools to loopback and silently ignores
# --remote-debugging-address. socat remains the network front-end, but each
# accepted connection now starts a browser on demand and is tracked by a
# per-helper marker. A connection held by Go's transport delays reap by its
# idle timeout; the 300-second threshold starts once the last connection closes.
reaper &
reaper_pid=$!
socat TCP-LISTEN:9222,reuseaddr,fork EXEC:'/entrypoint.sh connection',nofork &
front_pid=$!

stop_browser_gracefully() {
	lock
	if browser_alive; then
		# Chrome is a separate session, so stop its process group explicitly;
		# this gives its cookie batch time to flush before the container exits.
		stop_browser
	fi
	unlock
}

shutdown() {
	trap - INT TERM HUP
	stop_browser_gracefully
	kill "$front_pid" "$reaper_pid" 2>/dev/null || true
	exit 143
}
trap shutdown INT TERM HUP

if wait "$front_pid"; then
	status=0
else
	status=$?
fi
stop_browser_gracefully
kill "$reaper_pid" 2>/dev/null || true
exit "$status"