python扫描proxy并获取可用代理ip列表

mac或linux下可以work的代码如下：

# coding=utf-8

import requests
import re
from bs4 import BeautifulSoup as bs
import Queue
import threading
import random
import re

headers_useragents = []
headers_referers = []
headers_referers.append('http://www.google.com/?q=')
headers_referers.append('http://www.usatoday.com/search/results?q=')
headers_referers.append('http://engadget.search.aol.com/search?q=')
headers_useragents.append('Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.3) Gecko/20090913 Firefox/3.5.3')
headers_useragents.append(
    'Mozilla/5.0 (Windows; U; Windows NT 6.1; en; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
headers_useragents.append(
    'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.9.1.3) Gecko/20090824 Firefox/3.5.3 (.NET CLR 3.5.30729)')
headers_useragents.append('Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.1) Gecko/20090718 Firefox/3.5.1')
headers_useragents.append(
    'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.6 Safari/532.1')
headers_useragents.append(
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; InfoPath.2)')
headers_useragents.append(
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; SLCC1; .NET CLR 2.0.50727; .NET CLR 1.1.4322; .NET CLR 3.5.30729; .NET CLR 3.0.30729)')
headers_useragents.append('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Win64; x64; Trident/4.0)')
headers_useragents.append(
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; SV1; .NET CLR 2.0.50727; InfoPath.2)')
headers_useragents.append('Mozilla/5.0 (Windows; U; MSIE 7.0; Windows NT 6.0; en-US)')
headers_useragents.append('Mozilla/4.0 (compatible; MSIE 6.1; Windows XP)')
headers_useragents.append('Opera/9.80 (Windows NT 5.2; U; ru) Presto/2.5.22 Version/10.51')

class proxyPick(threading.Thread):
    def __init__(self, queue):
        threading.Thread.__init__(self)
        self._queue = queue

    def run(self):
        while not self._queue.empty():
            url = self._queue.get()

            proxy_spider(url)

def proxy_spider(url):
    headers = {
        #  .......
    }
    headers['User-Agent'] = random.choice(headers_useragents)
    headers['Cache-Control'] = 'no-cache'
    headers['Accept-Charset'] = 'ISO-8859-1,utf-8;q=0.7,*;q=0.7'
    headers['Referer'] = random.choice(headers_referers) + str(random.randint(5, 10))
    headers['Keep-Alive'] = str(random.randint(110, 120))
    headers['Connection'] = 'keep-alive'
    r = requests.get(url=url, headers=headers)
    soup = bs(r.content, "html.parser")
    data = soup.find_all(name='tr', attrs={'class': re.compile('|[^odd]')})

    for i in data:
        soup = bs(str(i), 'html.parser')
        data2 = soup.find_all(name='td')
        ip = str(data2[1].string)
        port = str(data2[2].string)
        types = str(data2[5].string).lower()

        proxy = {}
        proxy[types] = '%s:%s' % (ip, port)
        print proxy, " check proxy"
        try:
            proxy_check(proxy, ip)
        except Exception, e:
            print e
            pass

def proxy_check(proxy, ip):
    # url = 'http://1212.ip138.com/ic.asp'
    # url = 'https://www.ipip.net/ip.html'
    # url = 'http://www.baid.com'
    # url = 'http://ip138.com/'
    url = 'http://2018.ip138.com/ic.asp'
    r = requests.get(url=url, proxies=proxy, timeout=6)
    # r.encoding = 'gb2312' for url = 'http://ip138.com/'
    reip = r'\[(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\]'
    # print r.text
    f = open('ip_proxy.txt', 'a+')
    found = re.search(reip, r.text, re.M | re.I)
    if found:
        ip2 = found.group(1)
        print "ip==> : ", ip2
        if ip2 == ip:
            print "*" * 30
            print "ip is wanted:", ip
            f.write('%s' % proxy + '\n')
            print "*" * 30
    # import sys
    # sys.exit(0)
    f.close()

# proxy_spider()

def main():
    queue = Queue.Queue()
    for i in range(1, 2288):
        queue.put('http://www.xicidaili.com/nn/' + str(i))

    threads = []
    thread_count = 10

    for i in range(thread_count):
        spider = proxyPick(queue)
        threads.append(spider)

    for i in threads:
        i.start()

    for i in threads:
        i.join()

    print "It's down,sir!"

if __name__ == '__main__':
    main()

最后得到的可用结果就几个，蛋疼：

{'http': '118.190.95.43:9001'}
{'http': '118.190.95.35:9001'}
{'http': '101.236.35.98:8866'}
{'http': '101.236.23.202:8866'}
{'http': '175.11.213.25:808'}
{'http': '106.56.102.141:8070'}
{'http': '121.231.155.161:6666'}
{'http': '120.25.81.117:80'}
{'http': '117.63.78.100:6666'}
{'http': '111.231.115.150:8888'}
{'http': '222.185.23.251:6666'}
{'http': '106.56.102.107:8070'}
{'http': '118.114.77.47:8080'}
{'http': '115.28.90.79:9001'}
{'http': '58.57.75.142:63000'}

python扫描proxy并获取可用代理ip的实例

 from:https://www.jb51.net/article/120480.htm

 

下面小编就为大家带来一篇python扫描proxy并获取可用代理ip的实例。小编觉得挺不错的，现在就分享给大家，也给大家做个参考。一起跟随小编过来看看吧

 

今天咱写一个挺实用的工具，就是扫描并获取可用的proxy

首先呢，我先百度找了一个网站：http://www.xicidaili.com 作为例子

这个网站里公布了许多的国内外可用的代理的ip和端口

我们还是按照老样子进行分析，就先把所有国内的proxy扫一遍吧

点开国内部分进行审查发现，国内proxy和目录为以下url：

http://www.xicidaili.com/nn/x

这个x差不多两千多页，那么看来又要线程处理了。。。

老样子，我们尝试是否能直接以最简单的requests.get()获取内容

返回503，那么我们加一个简单的headers

返回200，成咯

好了我们先进行网页内容分析并获取想要的内容

我们发现，包含ip信息的内容在<tr>标签内，于是我们就能很方便的用bs进行获取标签内容

但是我们随之又发现，ip、端口、协议的内容分别在提取的<tr>标签的第2,3,6三个<td>标签内

r = requests.get(url = url,headers = headers) soup = bs(r.content,"html.parser") data = soup.find_all(name = 'tr',attrs = {'class':re.compile('|[^odd]')}) for i in data: soup = bs(str(i),'html.parser') data2 = soup.find_all(name = 'td') ip = str(data2[1].string) port = str(data2[2].string) types = str(data2[5].string).lower() proxy = {} proxy[types] = '%s:%s'%(ip,port)

这样，我们每次循环都能生成对应的proxy字典，以便我们接下来验证ip可用性所使用

字典这儿有个注意点，我们有一个将types变为小写的操作，因为在get方法中的proxies中写入的协议名称应为小写，而网页抓取的是大写的内容，所以进行了一个大小写转换

那么验证ip可用性的思路呢

很简单，我们使用get，加上我们的代理，请求网站：

http://1212.ip138.com/ic.asp

这是一个神奇的网站，能返回你的外网ip是什么

url = 'http://1212.ip138.com/ic.asp'
r = requests.get(url = url,proxies = proxy,timeout = 6)

这里我们需要加上timeout去除掉那些等待时间过长的代理，我设置为6秒

我们以一个ip进行尝试，并且分析返回的页面

返回的内容如下：

<html>

<head>

<meta xxxxxxxxxxxxxxxxxx>

<title> 您的IP地址 </title>

</head>

<body style="margin:0px"><center>您的IP是：[xxx.xxx.xxx.xxx] 来自:xxxxxxxx</center></body></html>

那么我们只需要提取出网页内[]的内容即可

如果我们的代理可用，就会返回代理的ip

（这里会出现返回的地址还是我们本机的外网ip的情况，虽然我也不是很清楚，但是我把这种情况排除，应该还是代理不可用）

那么我们就能进行一个判断，如果返回的ip和proxy字典中的ip相同，则认为这个ip是可用的代理，并将其写入文件

我们的思路就是这样，最后进行queue和threading线程的处理即可

上代码：

#coding=utf-8

import requests
import re
from bs4 import BeautifulSoup as bs
import Queue
import threading 

class proxyPick(threading.Thread):
 def __init__(self,queue):
  threading.Thread.__init__(self)
  self._queue = queue

 def run(self):
  while not self._queue.empty():
   url = self._queue.get()

   proxy_spider(url)

def proxy_spider(url):
 headers = {
   .......
  }

 r = requests.get(url = url,headers = headers)
 soup = bs(r.content,"html.parser")
 data = soup.find_all(name = 'tr',attrs = {'class':re.compile('|[^odd]')})

 for i in data:

  soup = bs(str(i),'html.parser')
  data2 = soup.find_all(name = 'td')
  ip = str(data2[1].string)
  port = str(data2[2].string)
  types = str(data2[5].string).lower() 

  proxy = {}
  proxy[types] = '%s:%s'%(ip,port)
  try:
   proxy_check(proxy,ip)
  except Exception,e:
   print e
   pass

def proxy_check(proxy,ip):
 url = 'http://1212.ip138.com/ic.asp'
 r = requests.get(url = url,proxies = proxy,timeout = 6)

 f = open('E:/url/ip_proxy.txt','a+')

 soup = bs(r.text,'html.parser')
 data = soup.find_all(name = 'center')
 for i in data:
  a = re.findall(r'\[(.*?)\]',i.string)
  if a[0] == ip:
   #print proxy
   f.write('%s'%proxy+'\n')
   print 'write down'

 f.close()

#proxy_spider()

def main():
 queue = Queue.Queue()
 for i in range(1,2288):
  queue.put('http://www.xicidaili.com/nn/'+str(i))

 threads = []
 thread_count = 10

 for i in range(thread_count):
  spider = proxyPick(queue)
  threads.append(spider)

 for i in threads:
  i.start()

 for i in threads:
  i.join()

 print "It's down,sir!"

if __name__ == '__main__':
 main()

这样我们就能把网站上所提供的能用的代理ip全部写入文件ip_proxy.txt文件中了

以上这篇python扫描proxy并获取可用代理ip的实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持脚本之家。