diff --git a/scrapy/Dockerfile b/scrapy/Dockerfile index d100de7..2cef1ad 100644 --- a/scrapy/Dockerfile +++ b/scrapy/Dockerfile @@ -2,11 +2,29 @@ # Dockerfile for scrapy # -FROM ubuntu:14.04 -MAINTAINER kev +FROM debian:jessie +MAINTAINER kev -RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv 627220E7 -RUN echo 'deb http://archive.scrapy.org/ubuntu scrapy main' >/etc/apt/sources.list.d/scrapy.list -RUN apt-get update && apt-get install -y python-pip scrapy-0.24 scrapyd +RUN apt-get update \ + && apt-get install -y build-essential \ + curl \ + libffi-dev \ + libssl-dev \ + libxml2-dev \ + libxslt1-dev \ + python \ + python-dev \ + && curl -sSL https://bootstrap.pypa.io/get-pip.py | python \ + && pip install scrapy==1.0.0rc1 + && apt-get remove -y build-essential \ + libffi-dev \ + libssl-dev \ + libxml2-dev \ + libxslt1-dev \ + python-dev \ + && apt-get autoremove -y \ + && apt-get install -y libxml2 \ + libxslt1.1 \ + && rm -rf /var/lib/apt/lists/* -CMD bash +CMD ["/bin/bash"] diff --git a/scrapy/Dockerfile.old b/scrapy/Dockerfile.old new file mode 100644 index 0000000..d100de7 --- /dev/null +++ b/scrapy/Dockerfile.old @@ -0,0 +1,12 @@ +# +# Dockerfile for scrapy +# + +FROM ubuntu:14.04 +MAINTAINER kev + +RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv 627220E7 +RUN echo 'deb http://archive.scrapy.org/ubuntu scrapy main' >/etc/apt/sources.list.d/scrapy.list +RUN apt-get update && apt-get install -y python-pip scrapy-0.24 scrapyd + +CMD bash diff --git a/scrapy/README.md b/scrapy/README.md new file mode 100644 index 0000000..d52dc8a --- /dev/null +++ b/scrapy/README.md @@ -0,0 +1,6 @@ +`Scrapy`: An open source and collaborative framework +for extracting the data you need from websites. +In a fast, simple, yet extensible way. + +You can create a scrapy (v1.0.0rc1) project on top of this image. +