Python采集代理ip并判断是否可用和定时更新的方法

网上有很多免费的ip地址,都是可以使用的,但是如果手动来获取太麻烦,这里通过Python自动抓取,可以批量获取。

代码如下:

# -*- coding: utf-8 -*-
import re
import urllib2
import json
import os
import time
import socket

class ProxyIp(object):
  def __init__(self):
    self.path = os.path.split(os.path.realpath(__file__))[0]
  # Get latest proxy ip and download to json
  def update_ip(self):
    print 'Update Ip'
    url = 'http://www.ip3366.net/free/'
    req = urllib2.Request(url)
    response = urllib2.urlopen(req)
    matches = re.findall(
      ur'(\d+.\d+.\d+.\d+)</td>\s+<td>(\d+)</td>\s+<td>.*?</td>\s+<td>(HTTPS?)</td>',
      response.read(),
      re.I
    )
    ls = []
    for match in matches:
      if self.is_open(match[0], match[1]):
        ls.append({'ip':match[0], 'port':match[1], 'protocol': match[2]})
    with open('%s/ip.json' % self.path, 'w') as f:
      json.dump(ls, f)
    return ls
  # whether the ips is last or old.
  def is_last(self):
    m_time = int(os.path.getmtime('%s/ip.json' % self.path))
    now_time = int(time.time())
    return (now_time - m_time) > 60*60*4 # 4 hours
  @staticmethod
  def is_open(ip, port):
    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    try:
      s.connect(ip, int(port))
      return True
    except:
      print 'Faild IP: %s:%s' % (ip, port)
      return False
  def get_proxy_ips(self):
    if not self.is_last():
      return self.update_ip()
    else:
      with open('%s/ip.json' % self.path, 'r') as f:
        return json.load(f)

相关推荐