dockerfiles/scrapyd/Dockerfile

#
# Dockerfile for scrapyd (python2) [deprecated]
#

FROM debian:buster
MAINTAINER EasyPi Software Foundation

ENV SCRAPY_VERSION=1.8.0
ENV SCRAPYD_VERSION=1.2.1
ENV SCRAPYRT_VERSION=0.11.0
ENV PILLOW_VERSION=6.2.2

RUN set -xe \
    && apt-get update \
    && apt-get install -y autoconf \
                          build-essential \
                          curl \
                          git \
                          libffi-dev \
                          libssl-dev \
                          libtool \
                          libxml2 \
                          libxml2-dev \
                          libxslt1.1 \
                          libxslt1-dev \
                          python \
                          python-dev \
                          tini \
                          vim-tiny \
    && apt-get install -y libtiff5 \
                          libtiff5-dev \
                          libfreetype6-dev \
                          libjpeg62-turbo \
                          libjpeg62-turbo-dev \
                          liblcms2-2 \
                          liblcms2-dev \
                          libwebp6 \
                          libwebp-dev \
                          zlib1g \
                          zlib1g-dev \
    && curl -sSL https://bootstrap.pypa.io/pip/2.7/get-pip.py | python \
    && pip install --no-cache-dir git+https://github.com/scrapy/scrapy.git@$SCRAPY_VERSION \
                   git+https://github.com/scrapy/scrapyd.git@$SCRAPYD_VERSION \
                   git+https://github.com/scrapy/scrapyd-client.git \
                   git+https://github.com/scrapinghub/scrapy-splash.git \
                   git+https://github.com/scrapinghub/scrapyrt.git@$SCRAPYRT_VERSION \
                   git+https://github.com/python-pillow/Pillow.git@$PILLOW_VERSION \
    && curl -sSL https://github.com/scrapy/scrapy/raw/master/extras/scrapy_bash_completion -o /etc/bash_completion.d/scrapy_bash_completion \
    && echo 'source /etc/bash_completion.d/scrapy_bash_completion' >> /root/.bashrc \
    && apt-get purge -y --auto-remove autoconf \
                                      build-essential \
                                      curl \
                                      libffi-dev \
                                      libssl-dev \
                                      libtool \
                                      libxml2-dev \
                                      libxslt1-dev \
                                      python-dev \
    && apt-get purge -y --auto-remove libtiff5-dev \
                                      libfreetype6-dev \
                                      libjpeg62-turbo-dev \
                                      liblcms2-dev \
                                      libwebp-dev \
                                      zlib1g-dev \
    && rm -rf /var/lib/apt/lists/*

COPY ./scrapyd.conf /etc/scrapyd/
VOLUME /etc/scrapyd/ /var/lib/scrapyd/
EXPOSE 6800

ENTRYPOINT ["tini", "--"]
CMD ["scrapyd", "--pidfile="]
add scrapyd 2014-12-01 15:19:37 +02:00			`#`
update scrapyd 2021-11-03 12:14:38 +02:00			`# Dockerfile for scrapyd (python2) [deprecated]`
add scrapyd 2014-12-01 15:19:37 +02:00			`#`

update scrapyd 2020-05-26 11:31:46 +02:00			`FROM debian:buster`
			`MAINTAINER EasyPi Software Foundation`

			`ENV SCRAPY_VERSION=1.8.0`
			`ENV SCRAPYD_VERSION=1.2.1`
update scrapyd 2021-03-29 09:39:47 +02:00			`ENV SCRAPYRT_VERSION=0.11.0`
update scrapyd 2020-05-26 11:31:46 +02:00			`ENV PILLOW_VERSION=6.2.2`
add scrapyd 2014-12-01 15:19:37 +02:00
add pillow to scrapyd to handle images 2016-05-26 14:30:59 +02:00			`RUN set -xe \`
			`&& apt-get update \`
update 2015-05-28 15:34:50 +02:00			`&& apt-get install -y autoconf \`
update 2015-05-28 01:21:59 +02:00			`build-essential \`
update 2015-05-28 15:34:50 +02:00			`curl \`
update 2015-05-28 17:29:07 +02:00			`git \`
update 2015-05-28 15:34:50 +02:00			`libffi-dev \`
			`libssl-dev \`
			`libtool \`
use libxml2-dev libxslt1-dev packages 2016-05-26 14:46:51 +02:00			`libxml2 \`
			`libxml2-dev \`
			`libxslt1.1 \`
			`libxslt1-dev \`
update 2015-05-28 15:34:50 +02:00			`python \`
update 2015-05-28 01:21:59 +02:00			`python-dev \`
update 2021-12-07 10:50:20 +02:00			`tini \`
update 2015-05-28 15:34:50 +02:00			`vim-tiny \`
add pillow to scrapyd to handle images 2016-05-26 14:30:59 +02:00			`&& apt-get install -y libtiff5 \`
			`libtiff5-dev \`
			`libfreetype6-dev \`
			`libjpeg62-turbo \`
			`libjpeg62-turbo-dev \`
			`liblcms2-2 \`
			`liblcms2-dev \`
fix scrapyd 2018-01-23 17:01:57 +02:00			`libwebp6 \`
add pillow to scrapyd to handle images 2016-05-26 14:30:59 +02:00			`libwebp-dev \`
			`zlib1g \`
			`zlib1g-dev \`
fix scrapyd 2021-11-17 10:59:20 +02:00			`&& curl -sSL https://bootstrap.pypa.io/pip/2.7/get-pip.py \| python \`
chore: Use --no-cache-dir flag to pip in Dockerfiles, to save space Using "--no-cache-dir" flag in pip install ,make sure dowloaded packages by pip don't cached on system . This is a best practise which make sure to fetch ftom repo instead of using local cached one . Further , in case of Docker Containers , by restricing caching , we can reduce image size. In term of stats , it depends upon the number of python packages multiplied by their respective size . e.g for heavy packages with a lot of dependencies it reduce a lot by don't caching pip packages. Further , more detail information can be found at https://medium.com/sciforce/strategies-of-docker-images-optimization-2ca9cc5719b6 Signed-off-by: Pratik Raj <rajpratik71@gmail.com> 2021-07-01 21:32:49 +02:00			`&& pip install --no-cache-dir git+https://github.com/scrapy/scrapy.git@$SCRAPY_VERSION \`
update scrapyd 2020-05-26 11:31:46 +02:00			`git+https://github.com/scrapy/scrapyd.git@$SCRAPYD_VERSION \`
update 2015-06-20 11:29:44 +02:00			`git+https://github.com/scrapy/scrapyd-client.git \`
add scrapyjs to scrapyd 2015-09-20 12:19:43 +02:00			`git+https://github.com/scrapinghub/scrapy-splash.git \`
update scrapyd 2021-03-29 09:39:47 +02:00			`git+https://github.com/scrapinghub/scrapyrt.git@$SCRAPYRT_VERSION \`
update scrapyd 2020-05-26 11:31:46 +02:00			`git+https://github.com/python-pillow/Pillow.git@$PILLOW_VERSION \`
update 2015-05-28 15:34:50 +02:00			`&& curl -sSL https://github.com/scrapy/scrapy/raw/master/extras/scrapy_bash_completion -o /etc/bash_completion.d/scrapy_bash_completion \`
			`&& echo 'source /etc/bash_completion.d/scrapy_bash_completion' >> /root/.bashrc \`
update 2015-06-20 11:12:04 +02:00			`&& apt-get purge -y --auto-remove autoconf \`
			`build-essential \`
update scrapyd 2020-05-29 06:11:32 +02:00			`curl \`
update 2015-06-20 11:12:04 +02:00			`libffi-dev \`
			`libssl-dev \`
			`libtool \`
use libxml2-dev libxslt1-dev packages 2016-05-26 14:46:51 +02:00			`libxml2-dev \`
			`libxslt1-dev \`
update 2015-06-20 11:12:04 +02:00			`python-dev \`
add pillow to scrapyd to handle images 2016-05-26 14:30:59 +02:00			`&& apt-get purge -y --auto-remove libtiff5-dev \`
			`libfreetype6-dev \`
			`libjpeg62-turbo-dev \`
			`liblcms2-dev \`
			`libwebp-dev \`
			`zlib1g-dev \`
fix 2015-05-28 01:30:09 +02:00			`&& rm -rf /var/lib/apt/lists/*`
update 2015-05-28 01:21:59 +02:00
add pillow to scrapyd to handle images 2016-05-26 14:30:59 +02:00			`COPY ./scrapyd.conf /etc/scrapyd/`
update 2015-05-28 17:11:37 +02:00			`VOLUME /etc/scrapyd/ /var/lib/scrapyd/`
			`EXPOSE 6800`
add scrapyd 2014-12-01 15:19:37 +02:00
update 2021-12-07 10:50:20 +02:00			`ENTRYPOINT ["tini", "--"]`
scrapyd: run without pidfile 2017-04-04 05:55:25 +02:00			`CMD ["scrapyd", "--pidfile="]`