selenium+phantomjs渲染网页

时间:2024-01-16 09:31:44
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
dcap = dict(DesiredCapabilities.PHANTOMJS)

#dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36 QIHU 360SE")
dcap["phantomjs.page.settings.userAgent"] = (random.choice(agents))
dcap["phantomjs.page.settings.loadImages"] = False
#dcap["phantomjs.page.settings.disk-cache"] = True
dcap["phantomjs.page.customHeaders.Cookie"] ='xxxxxxxxxx' #driver = webdriver.PhantomJS(executable_path='C:\\Python27\\phantomjs.exe', service_args=['--load-images=no'],desired_capabilities=dcap) #或者把phantomjs放在任何一个是环境变量文件夹的里面。
driver = webdriver.PhantomJS(executable_path='/home/yangdefeng/Downloads/phantomjs-2.1.1-linux-x86_64/bin/phantomjs',service_args=['--load-images=no'],desired_capabilities=dcap) #linux版本的需要修改phantomjs文件的权限,chmod u+x phantomjs,否则报错peimission delined 高并发 https://zhuanlan.zhihu.com/p/25507989 https://thief.one/2017/03/01/Phantomjs爬过的那些坑/