2018-09-12 00:42:40 +02:00
|
|
|
FROM python:3.6-alpine3.7
|
2018-05-03 10:22:10 +02:00
|
|
|
|
2018-09-12 00:42:40 +02:00
|
|
|
# Note: we pin selenium to 3.8.0 because of https://github.com/SeleniumHQ/selenium/issues/5296
|
|
|
|
RUN echo "http://dl-4.alpinelinux.org/alpine/v3.7/main" >> /etc/apk/repositories && \
|
|
|
|
echo "http://dl-4.alpinelinux.org/alpine/v3.7/community" >> /etc/apk/repositories && \
|
|
|
|
apk update && \
|
|
|
|
apk --no-cache add chromium chromium-chromedriver python3-dev build-base git && \
|
|
|
|
pip3 install --upgrade pip && \
|
|
|
|
pip3 install selenium==3.8.0 GitPython PyYAML beautifulsoup4==4.6.0 requests==2.18.4 responses==0.9.0 smmap2==2.0.3 urllib3==1.22 google-cloud-datastore==1.7.0 tenacity==5.0.2 && \
|
|
|
|
apk del python3-dev build-base
|
2018-05-03 10:22:10 +02:00
|
|
|
|
|
|
|
ADD spider.py /
|
2018-05-04 10:02:01 +02:00
|
|
|
ADD spider_test.py /
|
2018-08-23 09:37:53 +02:00
|
|
|
ADD data_export.py /
|
2018-05-03 10:22:10 +02:00
|
|
|
|
2018-05-03 12:01:30 +02:00
|
|
|
ENTRYPOINT ["python3"]
|
|
|
|
CMD ["/spider.py"]
|