模拟浏览器爬取-全球ping结果

import time
import csv
from urllib.parse import urlparse
from lxml import etree
from selenium import webdriver
from selenium. webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup as bs

# 定义谷歌webdriver
driver = webdriver.Chrome('E:/Anaconda/chromedriver')
base_url = 'https://www.wepcc.com'

def ping_(url_list):
    """
    输入一个url，输出全球ping的ip结果list
    """
    driver.maximize_window()  # 将浏览器最大化
    driver.get(base_url)  # 打开全球ping网站
    for url in url_list:
        element = driver.find_element_by_name("host")  # 找到输入框
        element.clear()  # 清空输入框
        element.send_keys(url)  # 写入要查询的url域名
        element.send_keys(Keys.RETURN)  # 模拟点击
        time.sleep(10)
        # element = driver.find_element_by_tag_name("table")
        # html解析
        soup = bs(driver.page_source, "html.parser")
        tags = soup.find_all('td', class_='r_ip')
        ip_li = []
        for ip in tags:
            if ip.text != 'loading':
                ip_li.append(ip.text)
        if len(set(ip_li)) > 1:
             print('{}的ip结果为{}，使用了cdn'.format(url, set(ip_li)))
        else:
            print('{}的ip结果为{}，未使用cdn'.format(url, set(ip_li)))
        driver.implicitly_wait(10) # seconds
    driver.quit()