scraping_docker

FROM python:3.7

RUN apt-get update && apt-get install -y --no-install-recommends wget gnupg curl
# Add chrome repository
RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add -
RUN sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list'

RUN apt-get update && apt-get install -y --no-install-recommends gcc libc-dev libmagic-dev unzip google-chrome-stable
RUN rm -rf /var/lib/apt/lists/*
RUN apt-get clean

# Install chromedriver
RUN DRIVER_VERSION=$(curl -sL http://chromedriver.storage.googleapis.com/LATEST_RELEASE)
RUN wget -O /tmp/chromedriver.zip http://chromedriver.storage.googleapis.com/`curl -sL http://chromedriver.storage.googleapis.com/LATEST_RELEASE`/chromedriver_linux64.zip
RUN unzip /tmp/chromedriver.zip chromedriver -d /usr/local/bin/

# Set display port to avoid crash on chrome
ENV DISPLAY=:99

COPY requirements.txt /tmp/
RUN pip install --no-cache-dir -r /tmp/requirements.txt
RUN useradd --create-home FAQ
WORKDIR home/FAQ/

COPY /FAQ FAQ/

ENV PYTHONPATH /home/FAQ

ENTRYPOINT ["python", "FAQ/scraper/run.py"]