mirror of
https://github.com/internetarchive/heritrix3.git
synced 2026-07-10 09:37:09 +00:00
55 lines
1.4 KiB
Docker
55 lines
1.4 KiB
Docker
ARG java=25-jdk-slim
|
|
|
|
FROM openjdk:${java}
|
|
|
|
ARG version="3.9.0"
|
|
ARG user="heritrix"
|
|
ARG userid=1000
|
|
|
|
LABEL version=${version}
|
|
LABEL user=${user}/$userid
|
|
|
|
# create user
|
|
RUN \
|
|
groupadd -g $userid $user && \
|
|
useradd -r -u $userid -g $user $user
|
|
|
|
# install dependencies and other requirements (for contrib)
|
|
RUN \
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
youtube-dl \
|
|
wget \
|
|
tar && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /opt
|
|
|
|
# download latest version according to:
|
|
# https://repo1.maven.org/maven2/org/archive/heritrix/heritrix-contrib
|
|
RUN \
|
|
wget -O heritrix-contrib-${version}-dist.tar.gz https://repo1.maven.org/maven2/org/archive/heritrix/heritrix-contrib/${version}/heritrix-contrib-${version}-dist.tar.gz && \
|
|
tar xvfz heritrix-contrib-${version}-dist.tar.gz && \
|
|
rm heritrix-contrib-${version}-dist.tar.gz && \
|
|
mv heritrix-contrib-${version} heritrix && \
|
|
chmod u+x heritrix/bin/heritrix && \
|
|
chown -R $user:$user /opt/heritrix
|
|
|
|
ADD entrypoint.sh /opt/entrypoint.sh
|
|
RUN chmod +x /opt/entrypoint.sh && \
|
|
chown $user:$user /opt/entrypoint.sh
|
|
|
|
WORKDIR /opt/heritrix
|
|
|
|
USER $user
|
|
|
|
ENV HERITRIX_HOME /opt/heritrix
|
|
# let it run in the foreground, required for docker
|
|
ENV FOREGROUND true
|
|
|
|
# standard webport
|
|
# NOTE: that the webpage is via HTTPS only available!
|
|
EXPOSE 8443
|
|
|
|
CMD ["/opt/entrypoint.sh"]
|