Closes #44. Chrome now starts on first CDP connection, tracks concurrent helpers, reaps after 300 seconds idle, preserves the named profile, and classifies reap interruptions. Shutdown stops Chrome's process group so cookie batches flush. ADR-0005 records the measured constraints and decisions. Verification: docker build, live CDP wake, graceful stop cleanup, sh -n, and go test ./... (7 packages, 3 no tests). Reviewed-on: #50 Co-authored-by: Sulthan Zaki <sultankiki05@gmail.com> Co-committed-by: Sulthan Zaki <sultankiki05@gmail.com>
This commit was merged in pull request #50.
This commit is contained in:
+190
-39
@@ -16,46 +16,197 @@ set -eu
|
||||
[ -n "${TZ:-}" ] || TZ=$(cat /etc/timezone 2>/dev/null || echo UTC)
|
||||
export TZ
|
||||
|
||||
# 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 (measured 2026-08-08, same host, same Chrome, only the
|
||||
# UA changed). Overriding it does not touch the Sec-CH-UA client hints, which
|
||||
# report the real version, so the version is read back out of the binary rather
|
||||
# than hardcoded: a hardcoded one would drift out of step with the hints on the
|
||||
# next Chrome update and become a fresh tell.
|
||||
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"
|
||||
|
||||
# Chrome binds its DevTools port to loopback and silently ignores
|
||||
# --remote-debugging-address (verified 2026-08-08: Chrome 151 with
|
||||
# --remote-debugging-address=0.0.0.0 still listened on 127.0.0.1 only), so the
|
||||
# caller — another container — cannot reach it directly. socat fronting the
|
||||
# loopback port is how chromedp/headless-shell solved the same problem and is
|
||||
# why this image is a drop-in for it.
|
||||
#
|
||||
# Nothing publishes 9222; reachability is the `browser` network in
|
||||
# docker-compose.yml, and an exposed CDP endpoint is remote code execution.
|
||||
socat TCP-LISTEN:9222,fork,reuseaddr TCP:127.0.0.1:9223 &
|
||||
lock() {
|
||||
flock 9
|
||||
}
|
||||
|
||||
# Chrome stays in the foreground so that its death takes the container down and
|
||||
# compose's restart policy applies; a backgrounded browser behind a live socat
|
||||
# would leave the sidecar looking healthy while answering nothing.
|
||||
#
|
||||
# No --enable-automation: it sets navigator.webdriver, the first thing a bot
|
||||
# check reads.
|
||||
#
|
||||
# --no-sandbox because Chrome's zygote wants user namespaces, which Docker's
|
||||
# default profile does not hand out; the alternative is --cap-add=SYS_ADMIN,
|
||||
# which gives the container strictly more than it takes away. Containment here
|
||||
# is the unprivileged user, the isolated network, and the fact that this
|
||||
# browser only ever navigates to kagane.to and novelfull.com.
|
||||
exec google-chrome-stable \
|
||||
--headless=new \
|
||||
--no-sandbox \
|
||||
--remote-debugging-port=9223 \
|
||||
--user-agent="$ua" \
|
||||
--user-data-dir=/home/chrome/profile \
|
||||
--no-first-run \
|
||||
--no-default-browser-check \
|
||||
--disable-gpu \
|
||||
about:blank
|
||||
unlock() {
|
||||
flock -u 9
|
||||
}
|
||||
|
||||
browser_alive() {
|
||||
[ -s "$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"
|
||||
|
||||
Reference in New Issue
Block a user