Created
July 20, 2016 20:58
-
-
Save ibnesayeed/b4cf439e21b35e9ab0ef1f44a4584a31 to your computer and use it in GitHub Desktop.
ArchiveSpark Docker image
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FROM jupyter/notebook | |
MAINTAINER Sawood Alam <ibnesayeed@gmail.com> | |
RUN apt-get update && apt-get install -y default-jre | |
RUN curl -L -O http://mirrors.ocf.berkeley.edu/apache/spark/spark-1.6.1/spark-1.6.1-bin-hadoop2.6.tgz \ | |
&& mkdir /spark \ | |
&& tar -xf spark-1.6.1-bin-hadoop2.6.tgz --strip-components=1 -C /spark \ | |
&& rm spark-1.6.1-bin-hadoop2.6.tgz | |
RUN curl -L -O http://l3s.de/~holzmann/archivespark-kernel.tar.gz \ | |
&& mkdir -p /root/.ipython/kernels \ | |
&& tar -xf archivespark-kernel.tar.gz -C /root/.ipython/kernels \ | |
&& rm archivespark-kernel.tar.gz | |
ADD kernel.json /root/.ipython/kernels/archivespark/kernel.json | |
ADD example.ipynb /notebooks/ | |
ADD cdx /cdx | |
ADD warc /warc | |
CMD ["jupyter", "notebook", "--no-browser"] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment