ArchiveBox/Dockerfile

48 lines
2 KiB
Docker
Raw Normal View History

2018-10-14 02:47:30 +00:00
FROM debian:stretch
2019-01-01 01:53:01 +00:00
LABEL maintainer="Nick Sweeting <archivebox-git@sweeting.me>"
2018-10-14 02:47:30 +00:00
RUN apt-get update \
2019-01-16 13:05:01 +00:00
&& apt-get install -qy git wget curl youtube-dl gnupg2 libgconf-2-4 python3 python3-pip \
2018-10-14 02:47:30 +00:00
&& rm -rf /var/lib/apt/lists/*
# Install latest chrome package and fonts to support major charsets (Chinese, Japanese, Arabic, Hebrew, Thai and a few others)
RUN apt-get update && apt-get install -y curl --no-install-recommends \
&& wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
&& sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google.list' \
&& apt-get update \
&& apt-get install -y chromium fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst ttf-freefont \
--no-install-recommends \
&& rm -rf /var/lib/apt/lists/* \
&& rm -rf /src/*.deb \
&& ln -s /usr/bin/chromium /usr/bin/chromium-browser
# It might be a good idea to use dumb-init to help prevent zombie chrome processes.
# ADD https://github.com/Yelp/dumb-init/releases/download/v1.2.0/dumb-init_1.2.0_amd64 /usr/local/bin/dumb-init
# RUN chmod +x /usr/local/bin/dumb-init
RUN git clone https://github.com/pirate/ArchiveBox /home/chromeuser/app \
2019-01-16 14:20:15 +00:00
&& pip3 install -r /home/chromeuser/app/archivebox/requirements.txt \
&& ln -s /home/chromeuser/app/bin/archivebox /usr/bin/archive
2018-10-14 02:47:30 +00:00
# Add user so we area strong, independent chrome that don't need --no-sandbox.
RUN groupadd -r chromeuser && useradd -r -g chromeuser -G audio,video chromeuser \
2019-01-16 13:05:01 +00:00
&& mkdir -p /data \
&& ln -s /data /home/chromeuser/app/archivebox/output \
2019-01-01 01:53:01 +00:00
&& chown -R chromeuser:chromeuser /home/chromeuser/app/archivebox/output \
2018-10-14 02:47:30 +00:00
&& chown -R chromeuser:chromeuser /home/chromeuser
2019-01-16 13:05:01 +00:00
VOLUME /data
2018-10-14 02:47:30 +00:00
ENV LANG=en_US.UTF-8 \
LANGUAGE=en_US:en \
LC_ALL=en_US.UTF-8 \
PYTHONIOENCODING=UTF-8 \
CHROME_SANDBOX=False \
2019-01-16 13:05:01 +00:00
OUTPUT_DIR=/data
2018-10-14 02:47:30 +00:00
# Run everything from here on out as non-privileged user
USER chromeuser
WORKDIR /home/chromeuser/app
2019-01-16 14:20:15 +00:00
CMD ["/usr/bin/archive"]