海运的博客

https://github.com/scrapinghub/portia

Windows下安装setuptools和pip：
https://bootstrap.pypa.io/ez_setup.py
https://bootstrap.pypa.io/get-pip.py

python ez_setup.py
python get-pip.py

安装selenium：

pip install selenium

安装PhantomJS：

https://bitbucket.org/ariya/phantomjs/downloads/phantomjs-1.9.7-linux-x86_64.tar.bz2
tar jxvf phantomjs-1.9.7-linux-x86_64.tar.bz2
cp phantomjs-1.9.7-linux-x86_64/bin/phantomjs /bin/
chmod 755 /bin/phantomjs 

使用示例：

from selenium import webdriver
driver = webdriver.PhantomJS()
driver.get("http://www.baidu.com")
data = driver.title
print data

通过Remote Selenium Server：

from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
driver = webdriver.Remote(
  command_executor='http://192.168.1.3:4444/wd/hub',
  desired_capabilities={'browserName': 'PhantomJS',
                                  'version': '2',
                                  'javascriptEnabled': True})
driver = webdriver.Remote(
   command_executor='http://192.168.1.3:4444/wd/hub',
   desired_capabilities=DesiredCapabilities.PHANTOMJS)
driver.get("http://www.baidu.com")
data = driver.title
print data

PhantomJS和Firefox速度对比：

import unittest
from selenium import webdriver
import time
class TestThree(unittest.TestCase):

    def setUp(self):
        self.startTime = time.time()

    def test_url_fire(self):
        self.driver = webdriver.Firefox()
        self.driver.get("http://www.qq.com")
        self.driver.quit()

    def test_url_phantom(self):
        self.driver = webdriver.PhantomJS()
        self.driver.get("http://www.qq.com")
        self.driver.quit()

    def tearDown(self):
        t = time.time() - self.startTime
        print "%s: %.3f" % (self.id(), t)
        self.driver.quit

if __name__ == '__main__':
    suite = unittest.TestLoader().loadTestsFromTestCase(TestThree)
    unittest.TextTestRunner(verbosity=0).run(suite)

远程连接chrome:

google-chrome --remote-debugging-port=9222 --no-sandbox

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

chrome_options = Options()
chrome_options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
driver = webdriver.Chrome(options=chrome_options)
driver.get("https://91porn.com")
html = driver.page_source
print(html)
time.sleep(2000)
driver.quit()

远程连接firefox：

firefox -marionette -start-debugger-server 2828

import time
from selenium import webdriver
from selenium.webdriver.firefox.service import Service

firefox_services = Service(executable_path='/usr/bin/geckodriver', port=3000, service_args=['--marionette-port', '2828', '--connect-existing'])
driver = webdriver.Firefox(service=firefox_services)
driver.get("https://91porn.com")
pageSource = driver.page_source
print(pageSource)
driver.quit()


#import time
#from selenium.webdriver import Firefox
#from selenium import webdriver

#driver = webdriver.Firefox()
#driver.get("https://91porn.com")
#html = driver.page_source
#print(html)
#time.sleep(2000)

#!/usr/bin/python
# -*- coding: utf-8 -*-  
from time import time
start = time()
stop = time()
print("程序执行时间"+str(stop-start) + "秒")