爬虫代理池的设置

下面介绍一段python爬虫的代理池

def get_ip_list():
    print("正在获取代理列表...")
    url = r'http://www.xicidaili.com/nn/'
    html = requests.get(url=url,headers=self.headers).text
    soup = BeautlfulSoup(html,'lxml')
    ips = soup.find(id='ip_list').find_all('tr')
    ip_list = []
    for i in range(1,len(ips)):
        ip_info = ips[i]
        tds= ip_info.find_all('td')
        ip_list.append(tds[1].text + ":" + tds[2].text)
    print("代理列表抓取成功")
    return ip_list

def get_random_ip(ip_list):
    print("正在设置随机代理...")
    proxy_list = []
    for ip in ip_list:
        proxy_list.append('http://' + ip)
    proxy_ip = random.choice(proxy_list)
    proxies = {'http':proxy_ip}
    print("代理设置成功")
    return proxies