1
0
Fork 0
archivebox/Dockerfile

286 lines
13 KiB
Text
Raw Normal View History

# This is the Dockerfile for ArchiveBox, it bundles the following dependencies:
2022-09-12 16:34:02 -04:00
# python3, ArchiveBox, curl, wget, git, chromium, youtube-dl, yt-dlp, single-file
2019-02-28 14:04:37 -05:00
# Usage:
# git submodule update --init --recursive
# git pull --recurse-submodules
# docker build . -t archivebox --no-cache
2020-07-22 01:30:58 -04:00
# docker run -v "$PWD/data":/data archivebox init
# docker run -v "$PWD/data":/data archivebox add 'https://example.com'
# docker run -v "$PWD/data":/data -it archivebox manage createsuperuser
# docker run -v "$PWD/data":/data -p 8000:8000 archivebox server
# Multi-arch build:
# docker buildx create --use
# docker buildx build . --platform=linux/amd64,linux/arm64,linux/arm/v7 --push -t archivebox/archivebox:latest -t archivebox/archivebox:dev
2022-09-11 16:13:22 -04:00
#
2023-10-20 08:10:03 -04:00
# Read more about [developing Archivebox](https://github.com/ArchiveBox/ArchiveBox#archivebox-development).
2019-02-28 14:04:37 -05:00
FROM debian:bookworm-backports
2023-10-20 08:10:03 -04:00
# Debian 12 w/ faster package updates: https://packages.debian.org/bookworm-backports/
2019-07-09 13:05:51 -04:00
2020-06-25 17:46:11 -04:00
LABEL name="archivebox" \
maintainer="Nick Sweeting <dockerfile@archivebox.io>" \
description="All-in-one personal internet archiving container" \
2020-11-23 02:04:39 -05:00
homepage="https://github.com/ArchiveBox/ArchiveBox" \
documentation="https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker"
2018-10-13 22:47:30 -04:00
ARG TARGETPLATFORM
ARG TARGETARCH
ARG TARGETVARIANT
######### Environment Variables #################################
# Global system-level config
2020-06-25 21:30:29 -04:00
ENV TZ=UTC \
2020-06-25 17:46:11 -04:00
LANGUAGE=en_US:en \
LC_ALL=C.UTF-8 \
2020-06-25 21:30:29 -04:00
LANG=C.UTF-8 \
DEBIAN_FRONTEND=noninteractive \
APT_KEY_DONT_WARN_ON_DANGEROUS_USAGE=1 \
PYTHONIOENCODING=UTF-8 \
PYTHONUNBUFFERED=1 \
npm_config_loglevel=error
2018-10-13 22:47:30 -04:00
# Version config
ENV PYTHON_VERSION=3.11 \
NODE_VERSION=21
# User config
ENV ARCHIVEBOX_USER="archivebox" \
DEFAULT_PUID=911 \
DEFAULT_PGID=911
# Global paths
ENV CODE_DIR=/app \
DATA_DIR=/data \
GLOBAL_VENV=/venv \
PLAYWRIGHT_BROWSERS_PATH=/browsers
# Application-level paths
ENV APP_VENV=/app/.venv \
NODE_MODULES=/app/node_modules
# Build shell config
ENV PATH="$PATH:$GLOBAL_VENV/bin:$APP_VENV/bin:$NODE_MODULES/.bin"
2023-10-31 06:06:02 -04:00
SHELL ["/bin/bash", "-o", "pipefail", "-o", "errexit", "-o", "errtrace", "-o", "nounset", "-c"]
######### System Environment ####################################
# Detect ArchiveBox version number by reading package.json
COPY --chown=root:root --chmod=755 package.json "$CODE_DIR/"
RUN grep '"version": ' "${CODE_DIR}/package.json" | awk -F'"' '{print $4}' > /VERSION.txt
# Print debug info about build and save it to disk
RUN (echo "[i] Docker build for ArchiveBox $(cat /VERSION.txt) starting..." \
&& echo "PLATFORM=${TARGETPLATFORM} ARCH=$(uname -m) ($(uname -s) ${TARGETARCH} ${TARGETVARIANT})" \
&& echo "BUILD_START_TIME=$(date +"%Y-%m-%d %H:%M:%S %s") TZ=${TZ} LANG=${LANG}" \
&& echo \
&& echo "GLOBAL_VENV=${GLOBAL_VENV} APP_VENV=${APP_VENV} NODE_MODULES=${NODE_MODULES}" \
&& echo "PYTHON=${PYTHON_VERSION} NODE=${NODE_VERSION} PATH=${PATH}" \
&& echo "CODE_DIR=${CODE_DIR} DATA_DIR=${DATA_DIR}" \
&& echo \
&& uname -a \
&& cat /etc/os-release | head -n7 \
&& which bash && bash --version | head -n1 \
&& which dpkg && dpkg --version | head -n1 \
&& echo -e '\n\n' && env && echo -e '\n\n' \
) | tee -a /VERSION.txt
# Create non-privileged user for archivebox and chrome
2023-10-31 06:06:02 -04:00
RUN echo "[*] Setting up $ARCHIVEBOX_USER user uid=${DEFAULT_PUID}..." \
2023-10-20 07:08:38 -04:00
&& groupadd --system $ARCHIVEBOX_USER \
&& useradd --system --create-home --gid $ARCHIVEBOX_USER --groups audio,video $ARCHIVEBOX_USER \
&& usermod -u "$DEFAULT_PUID" "$ARCHIVEBOX_USER" \
&& groupmod -g "$DEFAULT_PGID" "$ARCHIVEBOX_USER" \
&& echo -e "\nARCHIVEBOX_USER=$ARCHIVEBOX_USER PUID=$(id -u $ARCHIVEBOX_USER) PGID=$(id -g $ARCHIVEBOX_USER)\n\n" \
| tee -a /VERSION.txt
# DEFAULT_PUID and DEFAULT_PID are overriden by PUID and PGID in /bin/docker_entrypoint.sh at runtime
# https://docs.linuxserver.io/general/understanding-puid-and-pgid
# Install system apt dependencies (adding backports to access more recent apt updates)
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing APT base system dependencies for $TARGETPLATFORM..." \
# && echo 'deb https://deb.debian.org/debian bookworm-backports main contrib non-free' >> /etc/apt/sources.list.d/backports.list \
&& mkdir -p /etc/apt/keyrings \
&& apt-get update -qq \
&& apt-get install -qq -y --no-install-recommends \
# 1. packaging dependencies
apt-transport-https ca-certificates gnupg2 curl wget \
# 2. docker and init system dependencies
zlib1g-dev dumb-init gosu cron unzip grep \
# 3. frivolous CLI helpers to make debugging failed archiving easier
# nano iputils-ping dnsutils htop procps jq yq
&& rm -rf /var/lib/apt/lists/*
######### Language Environments ####################################
# Install Node environment
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing Node $NODE_VERSION environment in $NODE_MODULES..." \
&& echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_${NODE_VERSION}.x nodistro main" >> /etc/apt/sources.list.d/nodejs.list \
&& curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg \
2020-06-25 21:30:29 -04:00
&& apt-get update -qq \
&& apt-get install -qq -y -t bookworm-backports --no-install-recommends \
nodejs libatomic1 \
&& rm -rf /var/lib/apt/lists/* \
# Update NPM to latest version
&& npm i -g npm \
# Save version info
&& ( \
which node && node --version \
&& which npm && npm --version \
&& echo -e '\n\n' \
) | tee -a /VERSION.txt
# Install Python environment
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing Python $PYTHON_VERSION environment in $GLOBAL_VENV and $APP_VENV..." \
2023-10-20 07:08:38 -04:00
&& apt-get update -qq \
&& apt-get install -qq -y -t bookworm-backports --no-install-recommends \
2023-10-31 06:06:02 -04:00
python3 python3-pip python3-setuptools python3-wheel python3-venv python3-pdm python-dev-is-python3 \
#python3-ldap libldap2-dev libsasl2-dev libssl-dev python3-msgpack \
&& rm -rf /var/lib/apt/lists/* \
# tell PDM to allow using global system python site packages
&& rm /usr/lib/python3*/EXTERNALLY-MANAGED \
# create global virtual environment GLOBAL_VENV to use (better than using pip install --global)
2023-10-20 07:08:38 -04:00
&& python3 -m venv --system-site-packages --symlinks $GLOBAL_VENV \
# install global dependencies / python build dependencies in GLOBAL_VENV
2023-10-31 06:06:02 -04:00
&& $GLOBAL_VENV/bin/pip install --break-system-packages --upgrade pip pdm setuptools wheel \
# Save version info
&& ( \
which python3 && python3 --version | grep " $PYTHON_VERSION" \
&& which pip3 && pip3 --version \
&& which pdm && pdm --version \
&& echo -e '\n\n' \
) | tee -a /VERSION.txt
2020-04-22 21:13:49 -04:00
######### Extractor Dependencies ##################################
2020-09-08 18:12:55 -04:00
# Install apt dependencies
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing APT extractor dependencies globally using apt..." \
2023-10-20 07:08:38 -04:00
&& apt-get update -qq \
&& apt-get install -qq -y -t bookworm-backports --no-install-recommends \
curl wget git yt-dlp ffmpeg ripgrep \
# Packages we have also needed in the past:
# youtube-dl wget2 aria2 python3-pyxattr rtmpdump libfribidi-bin mpv \
# fontconfig fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst fonts-symbola fonts-noto fonts-freefont-ttf \
&& rm -rf /var/lib/apt/lists/* \
# Save version info
&& ( \
which curl && curl --version | head -n1 \
&& which wget && wget --version | head -n1 \
&& which yt-dlp && yt-dlp --version | head -n1 \
&& which git && git --version | head -n1 \
&& which rg && rg --version | head -n1 \
&& echo -e '\n\n' \
) | tee -a /VERSION.txt
2018-10-13 22:47:30 -04:00
# Install chromium browser using playwright
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing Browser binary dependencies to $PLAYWRIGHT_BROWSERS_PATH..." \
2023-10-20 07:08:38 -04:00
&& apt-get update -qq \
&& if [[ "$TARGETPLATFORM" == "linux/amd64" || "$TARGETPLATFORM" == "linux/arm64" ]]; then \
# install Chromium using playwright
$GLOBAL_VENV/bin/pip install playwright \
&& $GLOBAL_VENV/bin/playwright install --with-deps chromium \
&& export CHROME_BINARY="$($GLOBAL_VENV/bin/python -c 'from playwright.sync_api import sync_playwright; print(sync_playwright().start().chromium.executable_path)')"; \
else \
2023-10-31 06:06:02 -04:00
# fall back to installing Chromium via apt-get on platforms not supported by playwright (e.g. risc, ARMv7, etc.)
apt-get install -qq -y -t bookworm-backports --no-install-recommends \
chromium fontconfig fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst fonts-symbola fonts-noto fonts-freefont-ttf \
&& export CHROME_BINARY="$(which chromium)"; \
fi \
&& rm -rf /var/lib/apt/lists/* \
&& ln -s "$CHROME_BINARY" /usr/bin/chromium-browser \
&& mkdir -p "/home/${ARCHIVEBOX_USER}/.config/chromium/Crash Reports/pending/" \
&& chown -R $ARCHIVEBOX_USER "/home/${ARCHIVEBOX_USER}/.config" \
# Save version info
&& ( \
which chromium-browser && /usr/bin/chromium-browser --version \
&& echo -e '\n\n' \
) | tee -a /VERSION.txt
# Install Node dependencies
WORKDIR "$CODE_DIR"
2023-10-20 07:08:38 -04:00
COPY --chown=root:root --chmod=755 "package.json" "package-lock.json" "$CODE_DIR/"
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing NPM extractor dependencies from package.json into $NODE_MODULES..." \
2023-10-20 07:08:38 -04:00
&& npm ci --prefer-offline --no-audit \
&& ( \
which node && node --version \
&& which npm && npm version \
&& echo -e '\n\n' \
) | tee -a /VERSION.txt
######### Build Dependencies ####################################
2023-10-31 02:58:13 -04:00
# Install ArchiveBox Python dependencies
WORKDIR "$CODE_DIR"
2023-10-31 04:06:57 -04:00
COPY --chown=root:root --chmod=755 "./pyproject.toml" "./pdm.lock" "requirements.txt" "$CODE_DIR/"
2023-10-31 06:06:02 -04:00
RUN echo "[+] Installing PIP ArchiveBox dependencies from requirements.txt into $GLOBAL_VENV..." \
2023-10-31 02:58:13 -04:00
&& apt-get update -qq \
2023-10-31 06:06:02 -04:00
&& apt-get install -qq -y -t bookworm-backports --no-install-recommends \
build-essential libssl-dev libldap2-dev libsasl2-dev \
2023-10-31 04:05:39 -04:00
&& ln -s "$GLOBAL_VENV" "$APP_VENV" \
2023-10-31 06:06:02 -04:00
# && pdm use --venv in-project \
# && pdm run python -m ensurepip \
2023-10-31 04:05:39 -04:00
# && pdm sync --fail-fast --no-editable --group :all --no-self \
# && pdm export -o requirements.txt --without-hashes \
2023-10-31 06:06:02 -04:00
&& $GLOBAL_VENV/bin/pip install -r requirements.txt \
&& apt-get purge -y \
build-essential libssl-dev libldap2-dev libsasl2-dev \
# these are only needed to build CPython libs, we discard after build phase to shrink layer size
&& apt-get autoremove -y \
2023-10-31 02:58:13 -04:00
&& rm -rf /var/lib/apt/lists/*
# Install ArchiveBox Python package from source
2023-10-20 07:08:38 -04:00
COPY --chown=root:root --chmod=755 "." "$CODE_DIR/"
RUN echo "[*] Installing PIP ArchiveBox package from $CODE_DIR..." \
2023-10-20 07:08:38 -04:00
&& apt-get update -qq \
# install C compiler to build deps on platforms that dont have 32-bit wheels available on pypi
2023-10-31 02:34:24 -04:00
&& if [[ "$TARGETPLATFORM" == "linux/arm/v7" ]]; then \
2023-10-31 06:06:02 -04:00
apt-get install -qq -y --no-install-recommends build-essential python3-regex procps; \
else \
apt-get install -qq -y --no-install-recommends procps; \
2023-10-31 02:34:24 -04:00
fi \
# INSTALL ARCHIVEBOX python package globally from CODE_DIR, with all optional dependencies
2023-10-31 06:06:02 -04:00
&& $GLOBAL_VENV/bin/pip3 install --break-system-packages -e "$CODE_DIR"[sonic,ldap] \
# save docker image size and always remove compilers / build tools after building is complete
&& apt-get purge -y build-essential \
&& apt-get autoremove -y \
&& rm -rf /var/lib/apt/lists/*
####################################################
# Setup ArchiveBox runtime config
2023-10-20 07:08:38 -04:00
WORKDIR "$DATA_DIR"
ENV IN_DOCKER=True
## No need to set explicitly, these values will be autodetected by archivebox in docker:
# CHROME_SANDBOX=False \
# WGET_BINARY="wget" \
# YOUTUBEDL_BINARY="yt-dlp" \
# CHROME_BINARY="/usr/bin/chromium-browser" \
# USE_SINGLEFILE=True \
# SINGLEFILE_BINARY="$NODE_MODULES/.bin/single-file" \
# USE_READABILITY=True \
# READABILITY_BINARY="$NODE_MODULES/.bin/readability-extractor" \
# USE_MERCURY=True \
# MERCURY_BINARY="$NODE_MODULES/.bin/postlight-parser"
2018-10-13 22:47:30 -04:00
# Print version for nice docker finish summary
RUN (echo -e "\n\n[√] Finished Docker build succesfully. Saving build summary in: /VERSION.txt" \
&& echo -e "PLATFORM=${TARGETPLATFORM} ARCH=$(uname -m) ($(uname -s) ${TARGETARCH} ${TARGETVARIANT})" \
&& echo -e "BUILD_END_TIME=$(date +"%Y-%m-%d %H:%M:%S %s") TZ=${TZ}\n\n" \
&& "$CODE_DIR/bin/docker_entrypoint.sh" \
archivebox version 2>&1 \
) | tee -a /VERSION.txt
####################################################
2018-10-13 22:47:30 -04:00
# Open up the interfaces to the outside world
WORKDIR "$DATA_DIR"
VOLUME "$DATA_DIR"
EXPOSE 8000
2020-07-22 01:30:58 -04:00
2021-12-02 21:03:19 -05:00
# Optional:
# HEALTHCHECK --interval=30s --timeout=20s --retries=15 \
# CMD curl --silent 'http://localhost:8000/admin/login/' || exit 1
2021-02-17 18:24:38 -05:00
ENTRYPOINT ["dumb-init", "--", "/app/bin/docker_entrypoint.sh"]
2021-02-28 22:53:23 -05:00
CMD ["archivebox", "server", "--quick-init", "0.0.0.0:8000"]