在Scrapy中使用IP池或用户代理更新版（python3）

middlewares.py

# -*- coding: utf-8 -*-
# 导入随机模块
import random
# 导入有关IP池有关的模块
from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware
# 导入有关用户代理有关的模块
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware

# IP池
class HTTPPROXY(HttpProxyMiddleware):
    # 初始化 注意一定是 ip=''
    def __init__(self, ip=''):
        self.ip = ip

    def process_request(self, request, spider):
        item = random.choice(IPPOOL)
        try:
            print("当前的IP是："+item["ipaddr"])
            request.meta["proxy"] = "http://"+item["ipaddr"]
        except Exception as e:
            print(e)
            pass


# 设置IP池
IPPOOL = [
    {"ipaddr": "182.117.102.10:8118"},
    {"ipaddr": "121.31.102.215:8123"},
    {"ipaddr": "1222.94.128.49:8118"}
]


# 用户代理
class USERAGENT(UserAgentMiddleware):
    #初始化 注意一定是 user_agent=''
    def __init__(self, user_agent=''):
        self.user_agent = user_agent

    def process_request(self, request, spider):
        item = random.choice(UPPOOL)
        try:
            print("当前的User-Agent是："+item)
            request.headers.setdefault('User-Agent', item)
        except Exception as e:
            print(e)
            pass


# 设置用户代理池
UPPOOL = [
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36 Edge/14.14393"
]

settngs.py中添加一下代码（注意根据项目名修改指向，如这里的工程名是“的demo3”）

DOWNLOADER_MIDDLEWARES = {
    # 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware':123,
    # 'demo3.middlewares.HTTPPROXY' : 125,
    'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': 2,
    'demo3.middlewares.USERAGENT': 1
}