获取某网站提供的第一页的代理ip集，是函数形式

[python]代码库

def getDailiIPs(): # 获取某网站第一页的代理ip集
    url = 'http://www.xicidaili.com/nn/' # 这是国内高匿代理
    req = urllib.request.Request(url)
    req.add_header('User-Agent',
                   'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0')
    html = urllib.request.urlopen(req)
    bsObj = BeautifulSoup(html,'html.parser')

    all_ip = []
    all_duan = []
    tds = bsObj.findAll('td')
    for eachTd in tds:
        pipei_ip = re.search(r'(([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])\.){3}([01]{0,1}\d{0,1}\d|2[0-4]\d|25[0-5])',str(eachTd))  # 匹配每行是否有ip
        if pipei_ip != None:  # 如果这行有ip地址
            all_ip.append(pipei_ip.group())
        pipei_duankou = re.search(r'<td>([0-9]{0,1}){2,6}</td>', str(eachTd))
        if pipei_duankou != None:
            all_duan.append(pipei_duankou.group().lstrip('<td>').rstrip('</td>')) # 去掉前后的td标签
    all = []
    for each_ip in all_ip:
        each_duan = all_duan[all_ip.index(each_ip)]  # 得到ip对应的端口值
        all.append(each_ip + ':' + each_duan) # 组合成ip：端口的格式
    return all # 这里返回的是ip带端口集