参考博文https://www.cnblogs.com/shaosks/p/7278634.html

使用selenium的webdriver配合chrome实现了js页面的解析

配置了chrome×××面启动一直未生效

运行脚本发现启动chrome和登录过程都非常慢不明白原因

import datetime

import selenium

from selenium import webdriver

from selenium.webdriver.chrome.options import Options

from time import sleep

from pyquery import PyQuery as pq

host=["https://192.40.0.6/iPages/i_login.asp","https://192.40.0.7/iPages/i_login.asp","https://192.40.0.8/iPages/i_login.asp","https://192.40.0.9/iPages/i_login.asp","https://192.40.0.10/iPages/i_login.asp",

      "https://192.40.1.6/iPages/i_login.asp","https://192.40.1.7/iPages/i_login.asp","https://192.40.1.8/iPages/i_login.asp","https://192.40.1.9/iPages/i_login.asp","https://192.40.1.10/iPages/i_login.asp"]

for url in host:

opt = webdriver.ChromeOptions()

opt.set_headless()

browser = webdriver.Chrome(options=opt)

browser.get(url)

browser.find_element_by_id("username").send_keys("admin")

browser.find_element_by_id("password").send_keys("Passw0rd")

browser.find_element_by_id("loginButton").click()

sleep(1)

browser.switch_to.frame('mainFrame')   #处理页面框架的切换

#sleep(1)

browser.switch_to.frame('treeFrame')

selenium_html = browser.execute_script("return document.documentElement.outerHTML")   #返回页面的html元素

doc = pq(selenium_html)

dochtml = doc('a[id="Open_Problems_anchor"]')

strSources = dochtml.text().encode('utf8').strip()

txtsource = strSources[strSources.find('Open Problems') + 0:]    #提取指定元素的html

print (datetime.datetime.now().strftime('%m-%d %H;%M:%S'),url,txtsource)

browser.close()