WebScreenshot | 开发笔记

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
import sys
import os

def getUrls():
    urlsStr = ""
    # 从环境变量中获取
    envUrlsStr = os.getenv('URLS')
    urlsStr = envUrlsStr
    # 从命令行参数中获取
    if len(sys.argv) >= 2:
        argUrlsStr = sys.argv[1]
        if len(argUrlsStr) > 0:
            urlsStr = argUrlsStr
    urls = urlsStr.splitlines()

    return urls

def save_screenshot(url):
    driver.get(url)
    width = driver.execute_script("return document.documentElement.scrollWidth")
    height = driver.execute_script("return document.documentElement.scrollHeight")
    driver.set_window_size(width, height)
    driver.save_screenshot('./screenshots/' + time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) +'.png')
    
chrome_options = Options()
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument('--headless')
driver = webdriver.Chrome('./chromedriver', options=chrome_options)

urls = getUrls()
urlsLen = len(urls)
print('一共有: ' + str(urlsLen) + ' 条URL')
for i in range(0, urlsLen):
    time.sleep(5)
    save_screenshot(urls[i])
    print('截图成功: ' + urls[i])
    
print('运行完成')

name: Run App

on:
  push:
  schedule:
    # 定时任务，在每天的5点执行
    - cron: '0 21 * * *'

jobs:
  run-app:
    runs-on: ubuntu-latest

    steps:
    - uses: actions/checkout@v2
    - name: Set up Python 3.8
      uses: actions/setup-python@v2
      with:
        python-version: 3.8
        
    - name: Add conda to system path
      run: |
        # $CONDA is an environment variable pointing to the root of the miniconda directory
        echo $CONDA/bin >> $GITHUB_PATH
    
    - name: Install dependencies
      run: |
        sudo apt-get install unzip
        sudo pip install selenium
        # 安装 Chrome
        # 固定 Chrome 版本
        # 注意: Chrome 版本必须与 chromedriver 版本对应
        #sudo wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
        sudo dpkg -i google-chrome*.deb
        sudo apt-get install -f
        # TODO: 输出Chrome版本, 失败
        echo /usr/bin/google-chrome --version
        # 安装 chromedriver
        #sudo wget http://chromedriver.storage.googleapis.com/88.0.4324.96/chromedriver_linux64.zip
        sudo unzip chromedriver_linux64.zip
        # 为所有用户添加可执行权限 (对chromedriver文件)
        sudo chmod a+x chromedriver
        # 下面两行安装中文字体
        sudo apt install -y --force-yes --no-install-recommends fonts-wqy-microhei
        sudo apt install -y --force-yes --no-install-recommends ttf-wqy-zenhei
        
    - name: Run App
      run: |
        sudo python main.py '${{ secrets.URLS }}'
      # TODO: 发现这样设置环境变量，Python无法获取
      env:
        URLS: ${{ secrets.URLS }}
        TZ: Asia/Shanghai
    
    - name: Deploy 🚀
      uses: JamesIves/github-pages-deploy-action@3.7.1
      with:
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        BRANCH: gh-pages
        FOLDER: screenshots
        clean: false

FROM python:3.8 AS base

RUN apt-get install unzip
RUN pip install selenium
# 安装 Chrome
# TODO: 固定 Chrome 版本
# 注意: Chrome 版本必须与 chromedriver 版本对应
RUN wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
RUN dpkg -i google-chrome*.deb
RUN apt-get install -f
# TODO: 输出Chrome版本, 失败
RUN echo /usr/bin/google-chrome --version
# 安装 chromedriver
RUN wget http://chromedriver.storage.googleapis.com/88.0.4324.96/chromedriver_linux64.zip
RUN unzip chromedriver_linux64.zip
# 为所有用户添加可执行权限 (对chromedriver文件)
RUN chmod a+x chromedriver
# 下面两行安装中文字体
RUN apt install -y --force-yes --no-install-recommends fonts-wqy-microhei
RUN apt install -y --force-yes --no-install-recommends ttf-wqy-zenhei


ENTRYPOINT ["python", "main.py"]