python: 抓取免费代理ip

通过抓取西刺网免费代理ip实现代理爬虫：

from bs4 import BeautifulSoup
import requests
import random
import telnetlib
requests = requests.session()
ip_list = []
proxy_list = []
headers = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0',
     'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
]
headers = random.choice(headers)
headers = {'User-Agent': headers}
def get_proxy():
    url = 'http://www.xicidaili.com/nn/'
    web_data = requests.get(url, headers=headers)
    soup = BeautifulSoup(web_data.text, 'lxml')
    ips = soup.find_all('tr')
    for i in range(1, len(ips)):
        ip_info = ips[i]
        tds = ip_info.find_all('td')
        ip = tds[1].text
        port = tds[2].text
        try:
            telnetlib.Telnet(ip, port, timeout=2)
            ip_list.append(ip+":"+port)
        except:
            pass
    #print(ip_list)
    for ip in ip_list:
        proxy_list.append('http://' + ip)     
proxies = get_proxy()

proxy_ip = random.choice(proxy_list)
proxies = {'http': proxy_ip}
print(proxies)

代理IP的使用，把他传到get请求里面就可以了

requests.get(url, headers=headers, proxies=proxies)

转载于:https://blog.51cto.com/11962757/2093799