提取跳转链接

# -*- coding: utf-8 -*-

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from time import sleep
from urllib.parse import urlparse
#req_url = "http://www.hntlbj.com"
chrome_options=Options()
#设置chrome浏览器无界面模式
chrome_options.add_argument('--headless')
browser = webdriver.Chrome(options=chrome_options)
# 开始请求
urls = open("redirect","r")
out = open("output.txt","w")
for url in urls.readlines():
    url = url.strip().strip("\n")
    #print(url)
    #source_url = "http://"+url
    print("source_url:\t",url)
    a = urlparse(url)
    host1 = a.hostname
    try:
        browser.get(url)
    except:
        continue
    sleep(5)
    #打印页面网址
    re_url = browser.current_url
    re_url = re_url.strip()
    print("re_url:\t",re_url)
    o = urlparse(re_url)
    host2 = o.hostname
    if(host2 == host1):
        continue
    else:
        print("host:\t",re_url)
#关闭浏览器
browser.close()
#关闭chromedriver进程
browser.quit()