From 959a86983c502ef841b9f8735704b0902a555e43 Mon Sep 17 00:00:00 2001
From: MickLesk <47820557+MickLesk@users.noreply.github.com>
Date: Fri, 25 Sep 2026 14:30:30 +0200
Subject: [PATCH] Build the venv on the distro python and drop the obsolete
 extractors

A uv-managed interpreter lives where the service user cannot execute it, so every
archivebox call as that user died with 'Permission denied' while 0.9 drops privileges
on import; Debian 13 ships python3.13 in apt, so the venv now points at /usr/bin.
0.9 also provisions single-file and readability itself through abx-dl - the two npm
modules no longer exist - and it needs BASE_URL pinned plus tesseract, imagemagick,
ffmpeg, unzip and wget present, or archivebox install reaches for apt as a user that
has no root.
---
 ct/archivebox.sh              | 28 ++++++++++++++++++----------
 install/archivebox-install.sh | 31 +++++++++++++++++++++----------
 2 files changed, 39 insertions(+), 20 deletions(-)

diff --git a/ct/archivebox.sh b/ct/archivebox.sh
index 969094411..20bc8894c 100644
--- a/ct/archivebox.sh
+++ b/ct/archivebox.sh
@@ -13,7 +13,7 @@ var_cpu="${var_cpu:-2}"
 var_ram="${var_ram:-1024}"
 var_disk="${var_disk:-8}"
 var_os="${var_os:-debian}"
-var_version="${var_version:-12}"
+var_version="${var_version:-13}"
 var_arm64="${var_arm64:-yes}"
 var_unprivileged="${var_unprivileged:-1}"
 
@@ -31,20 +31,28 @@ function update_script() {
     exit
   fi
 
-  NODE_VERSION="22" NODE_MODULE="@postlight/parser@latest,single-file-cli@latest" setup_nodejs
-  export UV_PYTHON_INSTALL_DIR="/opt/archivebox/python"
-  PYTHON_VERSION="3.13" setup_uv
+  NODE_VERSION="22" setup_nodejs
+  setup_uv
 
-  ensure_dependencies chromium
+  ensure_dependencies chromium ripgrep tesseract-ocr tesseract-ocr-eng imagemagick ffmpeg unzip wget
 
   msg_info "Stopping Service"
   systemctl stop archivebox
   msg_ok "Stopped Service"
 
-  # Earlier installs used the system interpreter, which caps ArchiveBox at 0.7.4.
+  # Earlier installs used python3.11, which caps ArchiveBox at 0.7.4.
   if [[ ! -x /opt/archivebox/venv/bin/archivebox ]]; then
     msg_info "Moving ArchiveBox to its own Python 3.13 environment"
-    $STD uv venv --python 3.13 /opt/archivebox/venv
+    # The distro interpreter first: a uv-managed one lands where the service user cannot exec it.
+    local py="/usr/bin/python3.13"
+    if [[ ! -x "$py" ]]; then
+      ensure_dependencies python3.13 || true
+    fi
+    if [[ ! -x "$py" ]]; then
+      $STD uv python install --install-dir /opt/archivebox/python 3.13
+      py="$(UV_PYTHON_INSTALL_DIR=/opt/archivebox/python uv python find 3.13)"
+    fi
+    $STD uv venv --python "$py" /opt/archivebox/venv
     # Keep whatever port this container already answers on, or a reverse proxy in front
     # of it would silently stop resolving.
     local port
@@ -69,13 +77,13 @@ EOF
   fi
 
   msg_info "Updating ArchiveBox"
-  $STD uv pip install --python /opt/archivebox/venv/bin/python --upgrade archivebox playwright
-  $STD /opt/archivebox/venv/bin/playwright install-deps chromium
-  chown -R archivebox:archivebox /opt/archivebox/python /opt/archivebox/venv
+  $STD uv pip install --python /opt/archivebox/venv/bin/python --upgrade archivebox
+  chown -R archivebox:archivebox /opt/archivebox
   # Without this a shell still reaches the old 0.7.4 entry point against a 0.9 collection.
   ln -sf /opt/archivebox/venv/bin/archivebox /usr/local/bin/archivebox
   cd /opt/archivebox/data
   $STD sudo -u archivebox /opt/archivebox/venv/bin/archivebox init
+  $STD sudo -u archivebox /opt/archivebox/venv/bin/archivebox install
   msg_ok "Updated ArchiveBox"
 
   msg_info "Starting Service"
diff --git a/install/archivebox-install.sh b/install/archivebox-install.sh
index 0be91c585..3a7ccb54d 100644
--- a/install/archivebox-install.sh
+++ b/install/archivebox-install.sh
@@ -14,29 +14,34 @@ network_check
 update_os
 
 msg_info "Installing Dependencies"
+# ArchiveBox resolves these through its env provider, so it never has to reach for apt itself.
 $STD apt-get install -y \
   git \
-  libssl-dev \
-  libldap2-dev \
-  libsasl2-dev \
   procps \
   dnsutils \
+  chromium \
   ripgrep \
-  chromium
+  tesseract-ocr \
+  tesseract-ocr-eng \
+  imagemagick \
+  ffmpeg \
+  unzip \
+  wget \
+  python3.13
 msg_ok "Installed Dependencies"
 
+# No NODE_MODULE: 0.9 pulls single-file and readability itself, and postlight-parser is gone.
 NODE_VERSION="22" setup_nodejs
-UV_PYTHON_INSTALL_DIR="/opt/archivebox/python" PYTHON_VERSION="3.13" setup_uv
+setup_uv
 
 msg_info "Installing ArchiveBox"
-mkdir -p /opt/archivebox/{data,.npm,.cache,.local}
+mkdir -p /opt/archivebox/data
 $STD adduser --system --shell /bin/bash --gecos 'Archive Box User' --group --disabled-password --home /home/archivebox archivebox
-$STD uv venv --python 3.13 /opt/archivebox/venv
-$STD uv pip install --python /opt/archivebox/venv/bin/python archivebox playwright
-$STD /opt/archivebox/venv/bin/playwright install-deps chromium
+# The distro interpreter: a uv-managed one lands where the service user cannot execute it.
+$STD uv venv --python /usr/bin/python3.13 /opt/archivebox/venv
+$STD uv pip install --python /opt/archivebox/venv/bin/python archivebox
 ln -sf /opt/archivebox/venv/bin/archivebox /usr/local/bin/archivebox
 chown -R archivebox:archivebox /opt/archivebox
-chmod -R 755 /opt/archivebox/data
 msg_ok "Installed ArchiveBox"
 
 msg_info "Initializing ArchiveBox"
@@ -47,8 +52,14 @@ $STD sudo -u archivebox env \
   DJANGO_SUPERUSER_EMAIL=admin@archivebox.local \
   DJANGO_SUPERUSER_PASSWORD=community-scripts.org \
   /opt/archivebox/venv/bin/archivebox manage createsuperuser --noinput
+# Without a pinned canonical URL the admin greets every visitor with a red banner.
+$STD sudo -u archivebox /opt/archivebox/venv/bin/archivebox config --set "BASE_URL=http://$(get_ip):5797"
 msg_ok "Initialized ArchiveBox"
 
+msg_info "Installing Extractors"
+$STD sudo -u archivebox /opt/archivebox/venv/bin/archivebox install
+msg_ok "Installed Extractors"
+
 msg_info "Creating Service"
 cat <<EOF >/etc/systemd/system/archivebox.service
 [Unit]