爬取代理IP

爬取代理IP

目的

• 有时候需要使用代理IP，可用自己写一个爬取免费的代理IP，可用在需要的时候直接（import）导入即可

代码

import requests
from lxml import etree

ips = list()

"""国内免费代理"""


def h_proxies():
    url = 'https://www.kuaidaili.com/free/inha/1/'
    response = requests.get(url=url).content.decode()
    html = etree.HTML(response)
    proxy_info = html.xpath('//div/table/tbody/tr')

    for info in proxy_info:
        ip = info.xpath('./td[@data-title="IP"]/text()')
        port = info.xpath('./td[@data-title="PORT"]/text()')

        proxy_ip = ip[0] + ':' + port[0]
        ips.append(proxy_ip)

    return ips


"""国外免费代理"""


def f_proxies():
    url = 'https://ip.jiangxianli.com/?page=2'
    response = requests.get(url=url).content.decode()
    html = etree.HTML(response)
    proxy_info = html.xpath('//div/table/tbody/tr')

    for info in proxy_info:
        ip = info.xpath('./td[1]/text()')
        port = info.xpath('./td[2]/text()')

        proxy_ip = ip[0] + ':' + port[0]
        ips.append(proxy_ip)

    return ips


"""快代理"""


def k_proxies():
    url = 'https://www.kuaidaili.com/free/'
    response = requests.get(url=url).content.decode()
    html = etree.HTML(response)
    proxy_info = html.xpath('//div/table/tbody/tr')

    for info in proxy_info:
        ip = info.xpath('./td[1]/text()')
        port = info.xpath('./td[2]/text()')

        proxy_ip = ip[0] + ':' + port[0]
        ips.append(proxy_ip)

    return ips