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 enable_download_in_headless_chrome(driver, download_dir):
    driver.command_executor._commands["send_command"] = ("POST", '/session/$sessionId/chromium/send_command')
    params = {'cmd': 'Page.setDownloadBehavior', 'params': {'behavior': 'allow', 'downloadPath': download_dir}}
    driver.execute("send_command", params)


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)

    enable_download_in_headless_chrome(driver, DOWNLOAD_PATH)

    driver.get(URL)
    driver.execute_script("document.getElementsByTagName('a')[27].click()")

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


main()