ip可用测试

from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from selenium.common.exceptions import TimeoutException


proxies = ['223.111.131.100:8888',
           '47.94.234.50:8888',
           '111.29.3.187:8888',
        ]


u = 'http://mobile.cfda.gov.cn/datasearch/QueryRecord?tableId=43&searchF=ID&searchK=3'

for proxy in proxies:
    option = ChromeOptions()
    option.add_argument('--proxy-server={0}'.format(proxy))
    option.add_experimental_option('excludeSwitches',['enable-automation'])
    browser = webdriver.Chrome(options=option)
    browser.set_page_load_timeout(10)
    p = []
    try:
        browser.get(u)
        #browser.implicitly_wait(5)
        soup = BeautifulSoup(browser.page_source)
        browser.quit()
        p.append(proxy)
    except:
        browser.quit()
        print(proxy+'打开网页失败')

无用ip自动删除：

from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from selenium.common.exceptions import TimeoutException

def ip_judge(url,proxy):  
    '''
    判断ip是否可用 
    '''
    option = ChromeOptions()
    option.add_argument('--proxy-server={0}'.format(proxy))
    option.add_experimental_option('excludeSwitches',['enable-automation'])
    browser = webdriver.Chrome(options=option)
    browser.set_page_load_timeout(10)  
    try:
        browser.get(url)
        #browser.implicitly_wait(5)
        soup = BeautifulSoup(browser.page_source,"lxml")
        browser.quit()
        #p.append(proxy)
        return 'ok'
    except:
        browser.quit()
        #print(proxy+'打开网页失败')
        return 'no'

with open("E:\\testdata\\ipchi.txt",'r',encoding='utf-8-sig') as r:
    lines=r.readlines()

#u为测试网页 
u = 'http://baidu.com'

with open("E:\\testdata\\ipchi.txt",'w',encoding='utf-8') as w:
    for line in lines:
        judge = ip_judge(u,line.strip())
        if judge == 'no':
            continue
        w.write(line.strip()+'\n')