file download sample with headless chrome and docker

docker-compose.yml

version: '2'
services:
  scraping:
    image: scraping
    volumes:
      - .:/opt/app/scraping:rw

Dockerfile

FROM python:3.6-alpine3.7
ENV APP_ROOT=${APP_ROOT:-/opt/app}

# update apk repo
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

# install chromedriver
RUN apk update
RUN apk add chromium chromium-chromedriver
RUN apk add ttf-freefont

# install selenium
RUN pip install selenium

# install font
RUN mkdir /noto

ADD https://noto-website.storage.googleapis.com/pkgs/NotoSansCJKjp-hinted.zip /noto

WORKDIR /noto

RUN unzip NotoSansCJKjp-hinted.zip && \
    mkdir -p /usr/share/fonts/noto && \
    cp *.otf /usr/share/fonts/noto && \
    chmod 644 -R /usr/share/fonts/noto/ && \
    fc-cache -fv

WORKDIR $APP_ROOT/scraping

Makefile

DOCKER=docker

scraping:
	$(DOCKER) build -t scraping -f Dockerfile .

scraping.py

import time
from selenium import webdriver

URL = 'https://www.post.japanpost.jp/zipcode/dl/oogaki-zip.html'
DOWNLOAD_PATH = '/opt/app/scraping/dst'

def main():
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    options.add_argument('--no-sandbox')

    prefs = {"download.default_directory": DOWNLOAD_PATH, "download.prompt_for_download": False}
    options.add_experimental_option("prefs", prefs)
    driver = webdriver.Chrome(chrome_options=options)
    driver.get(URL)
    driver.execute_script("document.getElementsByTagName('a')[27].click()")

    time.sleep(3)
    driver.close()
    driver.quit()


main()