scrapy 使用中间件实现随机选择User_Agent以及Proxy

1.准备列表User_Agent 

USER_AGENTS = [
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5"
    ]

2.准备Proxy列表

IP代理可以网上搜索， 或者购买私密的代理IP

PROXIES = [
    {'ip_port': '111.8.60.9:8123', 'user_passwd': 'user1:pass1'},
    {'ip_port': '101.71.27.120:80', 'user_passwd': 'user2:pass2'},
    {'ip_port': '122.96.59.104:80', 'user_passwd': 'user3:pass3'},
    {'ip_port': '122.224.249.122:8088', 'user_passwd': 'user4:pass4'},
]

3.创建middlewares.py文件

# -*- coding:utf-8 -*-

import random
import base64

from settings import USER_AGENTS
from settings import PROXIES

# 随机的User-Agent
class RandomUserAgent(object):
    def process_request(self, request, spider):
        useragent = random.choice(USER_AGENTS)

        request.headers.setdefault("User-Agent", useragent)

class RandomProxy(object):
    def process_request(self, request, spider):
        proxy = random.choice(PROXIES)

        if proxy['user_passwd'] is None:
            # 没有代理账户验证的代理使用方式
            request.meta['proxy'] = "http://" + proxy['ip_port']
        else:
            # 对账户密码进行base64编码转换
            base64_userpasswd = base64.b64encode(proxy['user_passwd'])
            # 对应到代理服务器的信令格式里
            request.headers['Proxy-Authorization'] = 'Basic ' + base64_userpasswd
            request.meta['proxy'] = "http://" + proxy['ip_port']

 4.注册中间件类

DOWNLOADER_MIDDLEWARES = {
    #'mySpider.middlewares.MyCustomDownloaderMiddleware': 543,
    'mySpider.middlewares.RandomUserAgent': 1,
    'mySpider.middlewares.RandomProxy': 100
}