Python无头爬虫下载文件的实现

wget [https://dl.google.com/linux/direct/google-chrome-stable\_current\_x86\_64.rpm](https://dl.google.com/linux/direct/google-chrome-stable_current_x86_64.rpm)
yum install ./google-chrome-stable\_current\_x86\_64.rpm
yum install mesa-libOSMesa-devel gnu-free-sans-fonts wqy-zenhei-fonts

wget http://npm.taobao.org/mirrors/chromedriver/2.41/chromedriver_linux64.zip
unzip chromedriver\_linux64.zip
move chromedriver /usr/bin/
chmod +x /usr/bin/chromedriver

from selenium import webdriver
from time import sleep
from selenium.webdriver.chrome.options import Options
from selenium.common.exceptions import NoSuchElementException

chrome_options = Options()
chrome_options.add_argument('--no-sandbox')#解决DevToolsActivePort文件不存在的报错
chrome_options.add_argument('window-size=1920x3000') #指定浏览器分辨率
chrome_options.add_argument('--disable-gpu') #谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars') #隐藏滚动条, 应对一些特殊页面
chrome_options.add_argument('blink-settings=imagesEnabled=false') #不加载图片, 提升速度
chrome_options.add_argument('--headless') #浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败

prefs = {'profile.default_content_settings.popups': 0, 'download.default_directory': './filelist'}
chrome_options.add_experimental_option('prefs', prefs)

cls.driver=webdriver.Chrome(options=chrome_options)

cls.driver.quit()

cls.driver.get(url)

cls.driver.execute_script('console.log("helloworld")')

subtitle = cls.driver.find_element_by_class_name("fubiaoti").text