test sites

gistfile1.txt

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import re

sites=[]

dirver = webdriver.Chrome()

def load_page(site):
  start = time.time()
  dirver.get(site[4])
  end = time.time()
  elapsed = end -start
  print('====== end test - %s,%s,%s,%s seconds' % (site[0], site[3], site[4], elapsed))

def load_list(file):
  with open(file, 'r') as f:
    for line in f:
      arr = line.split(',')
      id = arr[0]
      kind = arr[1]
      region = arr[2]
      name = arr[3]
      url = arr[4]
      if not url.startswith('http'):
        url = 'https://' + url
      a = re.findall('https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+', url)
      load_page((id, kind, region, name, url))


def __main__():
  load_list('/Users/liangbo/Downloads/weblist.csv')
  dirver.close()

if __name__ == '__main__':
  __main__()