爬虫脚本代理池调度

有时在使用爬虫或者使用脚本需要频繁访问一个网站，这种时候很容易被服务器给ban掉ip，这种情况就可以使用代理池。从代理池中进行调度获取新的ip进行访问。

使用的是开源免费的python项目地址如下：
https://github.com/jhao104/proxy_pool

除了python还需要安装Redis

启动

启动redis

redis-server.exe redis.windows.conf

启动proxy_pool

启动调度程序

python proxyPool.py schedule

启动webApi服务

python proxyPool.py server

爬虫使用代理池

启动web服务后, 默认配置下会开启 http://127.0.0.1:5010 的api接口服务:

api	method	Description	params
/	GET	api介绍	None
/get	GET	随机获取一个代理	可选参数: ?type=https 过滤支持https的代理
/pop	GET	获取并删除一个代理	可选参数: ?type=https 过滤支持https的代理
/all	GET	获取所有代理	可选参数: ?type=https 过滤支持https的代理
/count	GET	查看代理数量	None
/delete	GET	删除代理	?proxy=host:ip

示例demo:

import requests

def get_proxy():
    return requests.get("http://127.0.0.1:5010/get/").json()

def delete_proxy(proxy):
    requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))

# your spider code

def getHtml():
    # ....
    retry_count = 5
    proxy = get_proxy().get("proxy")
    while retry_count > 0:
        try:
            print(proxy)
            html = requests.get('https://www.baidu.com', proxies={"http": "http://{}".format(proxy)})
            # 使用代理访问
            return html
        except Exception:
            retry_count -= 1
    # 删除代理池中代理
    delete_proxy(proxy)
    return None

if __name__ == '__main__':
    while(True):
        print(getHtml().text)

sqlmap使用代理池

获取所有的代理ip存入文件ips.txt（其他脚本同理）

import requests

def get_proxy():
    return requests.get("http://127.0.0.1:5010/all/").json()

def delete_proxy(proxy):
    requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))

def get_proxyCount():
    return requests.get("http://127.0.0.1:5010/count").json()

count = get_proxyCount().get('count').get('total')
print("代理池中共计：%s个代理." % count)


f = open("ips.txt", "w")
for i in range(count):
    b = get_proxy()[i].get('proxy')
    print(b)
    f.write(b + "\n")

print("over！")
f.close()

本地代理转发

借用前人的成果，实现的效果是启用本地192.168.3.17:9999服务，将ips.txt内的代理转发给本地客户端

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import socket
from socket import error
import threading
import random
import time

localtime = time.asctime(time.localtime(time.time()))


class ProxyServerTest:
    def __init__(self, proxyip):
        # 本地socket服务
        self.ser = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        self.proxyip = proxyip

    def run(self):
        try:
            # 本地服务IP和端口
            self.ser.bind(('192.168.3.17', 9999))
            # 最大连接数
            self.ser.listen(5)
        except error as e:
            print("[-]The local service : " + str(e))
            return "[-]The local service : " + str(e)

        while True:
            try:
                # 接收客户端数据
                client, addr = self.ser.accept()
                print('[*]accept %s connect' % (addr,))
                data = client.recv(1024)
                if not data:
                    break
                print('[*' + localtime + ']: Accept data...')
            except error as e:
                print("[-]Local receiving client : " + str(e))
                return "[-]Local receiving client : " + str(e)

            while True:
                # 目标代理服务器，将客户端接收数据转发给代理服务器
                mbsocket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
                iplen = len(self.proxyip)
                proxyip = self.proxyip[random.randint(0, iplen - 1)]
                print("[!]Now proxy ip:" + str(proxyip))
                prip = proxyip[0]
                prpo = proxyip[1]
                try:
                    mbsocket.settimeout(3)
                    mbsocket.connect((prip, prpo))
                except:
                    print("[-]RE_Connect...")
                    continue
                break

            #                   except :
            #                       print("[-]Connect failed,change proxy ip now...")
            #                      pass

            try:
                mbsocket.send(data)
            except error as e:
                print("[-]Sent to the proxy server : " + str(e))
                return "[-]Sent to the proxy server : " + str(e)

            while True:
                try:
                    # 从代理服务器接收数据，然后转发回客户端
                    data_1 = mbsocket.recv(1024)
                    if not data_1:
                        break
                    print('[*' + localtime + ']: Send data...')
                    client.send(data_1)
                except socket.timeout as e:
                    print(proxyip)
                    print("[-]Back to the client : " + str(e))
                    continue

            # 关闭连接

            client.close()
            mbsocket.close()


def Loadips():
    print("[*]Loading proxy ips..")
    ip_list = []
    ip = ['ip', 'port']
    with open("ips.txt") as ips:
        lines = ips.readlines()

    for line in lines:
        ip[0], ip[1] = line.strip().split(":")
        ip[1] = eval(ip[1])
        nip = tuple(ip)
        ip_list.append(nip)
    return ip_list


def main():
    print('''*Atuhor : V@1n3R.

*Blog :http://www.Lz1y.cn
*date: 2017.7.17
*http://www.Lz1y.cn/wordpress/?p=643





                         __     __    _       _____ ____    

                         \ \   / /_ _/ |_ __ |___ /|  _ \   

                          \ \ / / _` | | '_ \  |_ \| |_) |  

                           \ V / (_| | | | | |___) |  _ < _ 

                            \_/ \__,_|_|_| |_|____/|_| \_(_) 






    ''')

    ip_list = Loadips()
    #   ip_list = [('118.89.148.92',8088)]
    #   ip_list = tuple(ip_list)
    try:
        pst = ProxyServerTest(ip_list)
        # 多线程
        t = threading.Thread(target=pst.run, name='LoopThread')
        print('[*]Waiting for connection...')
        # 关闭多线程
        t.start()
        t.join()
    except Exception as e:
        print("[-]main : " + str(e))
        return "[-]main : " + str(e)


if __name__ == '__main__':
    main()

sqlmap使用 --proxy进行调用

免费的代理池，有的ip质量不行会连不上